This does not mean agents are inherently malicious. It means they are capable tools that can be granted access to important systems by users. They can make mistakes, be manipulated, or be compromised. Their models can produce variable outputs, their context can change, and their plans can evolve as they work. An agent that operates as intended when a task begins may respond differently as context or inputs change. Depending on how they are designed and deployed, agents can operate continuously, at machine speed and scale.

Satya Nadella, Chairman and Chief Executive Officer of Microsoft, recently described the trust architecture this new era requires: we must separate the supply of intelligence from the authority over it. We should not ask a model to be its own security authority. The controls that determine what it can access, what actions it can take, and whether it should continue operating must sit outside the model, where the model cannot bypass or tamper with them.

Project Perception—Securing your agentic insider

We introduced Project Perception and the Microsoft cyber stack to help organizations defend with agents. Today, we are extending Perception to secure the agentic insider. Guardian Agents help security teams operate continuously, at machine speed and scale, while sensors, context, and actuators across the cyber stack help understand changing agent risk and continuously adapt protection in response. Project Perception and Microsoft Agent 365 share signals, context, and a unified registry giving IT and security teams a consistent view of agents and risk, with the controls each needs.

This builds on a simple security principle: surround non-deterministic intelligence with deterministic controls, independent evidence, and containment boundaries. Assume an agent can fail or be compromised. Observe it continuously. Minimize and tailor its authority before it acts. And continuously adjust that authority as risk changes.

This requires protection across identity, permissions, data, endpoints, network, cloud, and runtime. The system has four continuous responsibilities:

• Know which agents exist, who owns them, why they exist, and what they are doing.
• Contain what each agent can access and do before it acts.
• Protect the data, tools, runtime, resources, and systems in the agent’s path.
• Adapt protection continuously as behavior, context, and risk change.

These are not four products or sequential phases. They operate together. Evidence changes risk. Risk changes policy. Policy changes what the agent is allowed to do. Consider an expense-approval agent. It may need to read expense submissions, check policy, and approve routine reimbursements, but it should not inherit every permission of the employee who sponsors it. Its identity, runtime, access paths, and task-scoped authority should be explicit from the start. If it later encounters a prompt injection or attempts an action outside that task, the system should respond proportionately: preserve safe reads while blocking writes, narrow the resources it can reach, require provable human approval for a consequential step, or isolate and stop the agent when the risk warrants it. This is what continuous containment looks like in practice.

Know every agent and give it an accountable identity

You cannot secure what you cannot see. Agents can be created through Microsoft platforms, integrated through partner platforms and software development kits (SDKs), or introduced locally without a central deployment process. Microsoft Security uses native integrations, connectors, and sensors across the cyber stack to discover more of the agent estate.

We are expanding discovery to 35 additional types of local agents, bringing the total to 60 supported local agents, including Claude Code, OpenAI Codex, and GitHub Copilot. Organizations can bring these agents into a unified registry, regardless of how they were discovered, to understand ownership, activity, and risk.

Discovery tells you that an agent exists. Identity gives security and governance systems a durable anchor for controlling it.

Every agent should have a first-class identity distinct from the person using or sponsoring it. We are extending Microsoft Entra Agent ID with identity types for additional agent patterns, including local and previously unknown agents discovered through security sensors. This means an agent can become a policy target even when it was not originally integrated with Microsoft Security. Agent identity anchors attribution, ownership, lifecycle, risk, permissions, authorization, and policy, so the enterprise can distinguish what a person did from what an agent did on that person’s behalf.

Contain what the agent can do before it acts

Being able to find and identify an agent is necessary, but it is just the start. We need to understand the potential impact the agent can have in the enterprise environment. The next step is to bound the agent across its runtime, its paths to tools and resources, and the authority it can exercise.

Contain the runtime

The model and harness should execute inside a controlled environment rather than inherit fully-privileged access to the device. Sandboxes such as Microsoft Execution Container (MXC) provide policy-controlled access to resources the agent needs to complete its task. They also create an enforcement boundary where security controls and observability can operate outside the agent’s reach. If the agent or harness is compromised, it should not be able to disable the controls watching it.

Control the action space

An agent should not be free to call any tool, API, Model Context Protocol (MCP) server, resource, or other agent it can find. Local and network and data controls must mediate those paths, observe the calls, and enforce enterprise policy. Controlling the destination alone is not enough. Security must also understand the content flowing into and out of the agent, including its sensitivity, provenance, and whether untrusted data may be influencing the agent’s behavior.

Start with no permissions, or least privilege

We have spent decades applying Zero Trust and least privilege to people. Agents make those principles even more important. An agent should not automatically inherit all the standing access of its user. It should begin with no authority and receive only what it needs for the approved task, for only as long as the task requires.

To enable this, we are introducing Dynamic Permissions. Organization-wide policy sets the outer boundary, including preventing an agent from obtaining authority its user does not have. Permissions can then be scoped to the task, made time-bound, and contracted or removed as the task changes or completes. Higher-impact actions can require verified human approval.

Adapt protection as agent risk changes

Least privilege reduces exposure, but it does not eliminate risk. An expense-approval agent may begin a task with the right access and then encounter a prompt injection in an external document. Its configuration has not changed, but its behavior and risk have.

For human users, a delay between detection and response may be manageable. For an agent operating at machine speed, it can be the difference between containment and impact. The security system must be able to understand what changed and act before a person can manually investigate every signal.

That is why we are introducing Dynamic Agent Risk and Dynamic Conditional Access for agents.

Dynamic Agent Risk

Dynamic Agent Risk combines signals from identity, data, endpoints, cloud, network, runtime, and the agent’s own activity. It considers how securely the agent is configured, what resources it can reach, the potential impact if something goes wrong, and whether its actions are drifting from the user’s or organization’s intent.

The result is not a one-time score assigned at onboarding. It is a continuously updated understanding of the agent’s current risk and whether its current authority still matches that risk. The question is not simply whether the agent should run or stop. It is what the agent should be allowed to read, change, invoke, or approve at that moment.

Dynamic Conditional Access

Dynamic Conditional Access extends Microsoft Entra Conditional Access for agents so a change in risk can drive coordinated action across multiple enforcement points. The response is graduated, not binary. Policy can reduce permissions, preserve reads while blocking writes, narrow the data and resources the agent can reach, restrict network paths, shorten or revoke time-bound access, or require provable human approval before a consequential action proceeds. At the highest levels of risk, it can isolate the runtime or stop execution entirely.

Return to the expense agent. It begins with narrowly scoped permission to review and approve expenses within policy. When it encounters untrusted content and attempts an unrelated action, new evidence raises its Dynamic Agent Risk. Policy responds proportionately: it can preserve read access while removing the ability to approve or write, block access to sensitive resources, and require cryptographically provable human approval for a high-impact step. If the risk continues to rise, the system can isolate the runtime or stop execution. The employee remains productive. The agent is constrained without treating every risk change as a kill-switch event.

Secure agentic systems at scale with Guardian Agents

As organizations deploy thousands or hundreds of thousands of agents, manually triaging every alert and coordinating every response will not scale. Securing agents must itself become agentic, while remaining inside boundaries people set.

That is why we are introducing new Playbooks and a team of Guardian Agents in Project Perception. People define policy, approval boundaries, and delegation rules. Playbooks define the desired security outcome and coordinate protective actions. Guardian Agents carry out the work at machine speed, adapting as agent activity, risk, security context, and organizational policy change.

Guardian Agents can help teams understand why risk changed, investigate the relevant evidence, recommend or apply containment, and use what they learn to harden policy. This is not about outsourcing judgment. People retain control over objectives and consequential decisions. The system carries the continuous work that does not scale through manual operations.

Agents will only be adopted at scale if they can be trusted at scale. At Microsoft, we are already operating in a world of hundreds of thousands of agents. As Customer Zero, we have learned that securing agents requires continuous visibility into agent activity, proactive protection of access and data, and adaptive protection that keeps pace with evolving threats. Those lessons directly inform the innovations we are delivering to help every organization adopt agents with confidence.”

—Terrell Cox, Corporate Vice President (CVP) and Deputy Chief Information Security Officer (CISO), Customer Security, Microsoft

Extending containment to the model

As model transparency increases, it creates a new source of security evidence. Chain-of-thought and other model-level signals can help identify intent drift, understand whether untrusted information is influencing reasoning, and detect when an agent’s planned actions are diverging from the task it was given.

We are bringing this deeper evidence into Dynamic Agent Risk, together with signals from across the cyber stack. This builds on Satya Nadella’s principle: increase transparency into the model while keeping security decisions and enforcement independent of it.

Greater model transparency gives security systems deeper evidence to detect suspicious behavior and inform Dynamic Agent Risk. But the core security principle does not change: the model cannot be its own security boundary. Independent systems must observe every layer, including the model itself, and ultimately determine and enforce what the system is allowed to do.

These are not separate pillars. They make the same containment architecture stronger: better evidence, stronger assurance, more accurate risk, and more effective protection.

Confidence to move faster

Organizations are adopting agents to serve customers better, solve problems faster, and give people more time for the work that matters most. The goal is not to make every model perfectly predictable before it can be useful. The goal is to build systems that remain secure even when the model is not.

That requires a clear division of responsibility. Models supply intelligence. People and organizations retain authority. Independent controls establish identity, limit privilege, protect data, preserve evidence, and contain unsafe action. Security continuously reassesses risk and adapts protection as the agent works.

That is what we are working toward: an agentic world where organizations can put intelligence to work with confidence because security can observe it, govern it, and contain it at the same speed.

Learn more here and join us at Microsoft Ignite.

To learn more about Microsoft Security solutions, visit our website. Bookmark the Security blog to keep up with our expert coverage on security matters. Also, follow us on LinkedIn (Microsoft Security) and X (@MSFTSecurity) for the latest news and updates on cybersecurity.

The post Agents are your newest insiders. Security must move at their speed.  appeared first on Microsoft Security Blog.

While that flexibility can be valuable, it also affects how enterprises evaluate models, where they implement safeguards, and who is responsible for maintaining those safeguards over time.

As enterprises choose which models to deploy, the relevant question is broader than whether a model is open-weight or closed-weight. Enterprises need to understand what they are using the model for, what could go wrong in that context, and what evidence and controls they need to manage risks.

Today, Microsoft and NVIDIA are publishing Risk Management for Open-Weight Models in Enterprise, the first in a planned series of joint resources intended to help enterprises address those questions. The paper introduces a shared risk taxonomy and an approach to managing model risks grounded in established standards and frameworks, including International Organization for Standardization (ISO) standards and the National Institute of Standards and Technology (NIST) AI Risk Management Framework.

The paper reflects a core idea: weight openness alone does not determine an AI system’s risk. Risk depends on the model, use case, deployment, and safeguards.

Understanding risk in the deployment context

Open- and closed-weight models can share many of the same underlying risks, but how those risks materialize depends on the deployment. A model used to help an employee draft a document presents different considerations than the same model used in a customer-facing workflow, just as a standalone inference endpoint differs from a system connected to external data or tools.

The architecture matters too. A risk may originate in the model, while the most effective control may sit in the inference environment, application, or surrounding operational processes. The joint guidance looks beyond the model label to factors including provenance, intended use, users, deployment conditions, and surrounding controls. This first paper focuses primarily on model-layer risks. Evaluating a model alone does not establish the safety of an agent or application: teams must also assess its permissions, data access, tools, runtime, and operational controls.

Establishing a common language

Managing these risks consistently also requires a common vocabulary across engineering, security, legal, safety, and business teams.

The initial Microsoft and NVIDIA taxonomy organizes risks into five broad categories: Cybersecurity, Data Protection, Content, Human-AI Interaction, and Bias. It is not a policy or deployment checklist, but instead it should be used by enterprises to adapt it to their own systems, use cases, and risk criteria, then connect relevant risks to evaluations, mitigations, and accountable owners.

Using evaluations as risk evidence

Evaluations help turn the taxonomy into something enterprises can use. The paper maps evaluations to a selection of risks across the five categories, giving teams a way to start with a risk that matters for their deployment and identify evaluations that can produce relevant evidence about it.

Microsoft Foundry helps enterprises assess quality, groundedness, and safety with built-in and custom evaluations and automated red teaming. Its configurable content-safety controls help detect and mitigate harmful inputs and outputs and prompt attacks. Teams should validate control availability for their model and deployment, including preview status, and combine these capabilities with application-specific testing, monitoring, and human oversight.

Evaluations still need to be interpreted in the context of a particular deployment and the goal is to make it easier for teams to connect the risks they identify with useful evidence, while building a broader set of evaluation resources that can evolve alongside models, deployment patterns, and emerging risks. Microsoft and NVIDIA plan to use the joint repository to share additional evaluations and point to existing resources that can help enterprises assess specific risks.

Accounting for changes in control and responsibility

Open-weight access gives enterprises greater control over how a model is evaluated, modified, and deployed. Model access and deployment are separate choices: open-weight models can also be used through managed platforms. Responsibility for safeguards depends on the service and deployment configuration; enterprises that operate their own model deployments may take on controls otherwise provided by a managed service.

Those safeguards can operate at different layers, and (depending on the risk) enterprises might use model changes, access controls, input and output filtering, monitoring, or human review. The important step is connecting each identified risk to controls that can effectively address it within the deployed system. Those decisions need to be revisited as models and deployments change.

Building on this work

Risk Management for Open-Weight Models in Enterprise focuses primarily on the model layer. Future work from Microsoft and NVIDIA is intended to extend this approach across the runtime, harness, and application layers, with additional technical guidance on evaluation and mitigation.

We also expect the resources supporting this work to evolve as new models, evaluations, and deployment patterns emerge. The joint repository will provide a place to share additional evaluation resources, including contributions from the broader community.

For enterprises deploying open-weight models today, the paper provides guidance they can begin applying to their own use cases. We encourage developers, security practitioners, researchers, and others working in this space to read the paper, explore the evaluations, and contribute evaluations that can help strengthen this shared body of work.

Read the joint Microsoft-NVIDIA paper, Risk Management for Open-Weight Models in Enterprise.

Explore the joint repository and technical resources.

Risk Management for Open-Weight Models in Enterprise was developed jointly by Microsoft and NVIDIA, with Andrew Berkley and April Chen of Microsoft and Michael Boone, Eileen Long, and Arun Rao of NVIDIA leading the development and editing of the paper.

Explore Microsoft Foundry evaluations and content-safety controls for implementation guidance.

To learn more about Microsoft Security solutions, visit our website. Bookmark the Security blog to keep up with our expert coverage on security matters. Also, follow us on LinkedIn (Microsoft Security) and X (@MSFTSecurity) for the latest news and updates on cybersecurity.

The post Managing open-weight model risk in enterprise deployments appeared first on Microsoft Security Blog.

We see that across the report. Threat activity can span infrastructure, identities, applications, cloud environments, and software supply chains. AI systems and agents increasingly interact with data, tools, and business systems. And activity that looks incomplete in one part of an environment can become clearer when separate signals are considered together. That makes the connections across an environment increasingly relevant to how we understand both cyberthreats and defense.

The pace of change also matters. AI models are becoming more capable, automation is expanding, and new connections are forming across the systems organizations rely on. These developments can change the speed and scale of security activity even as the underlying security fundamentals remain familiar.

Several findings in this year’s report illustrate that.

AI in the threat landscape

Threat actors are incorporating AI into reconnaissance, social engineering, malware and exploit development, and post-compromise activity. For now, much of their use remains focused on specific parts of existing attack workflows, even as more advanced applications of AI continue to develop.

AI can give threat actors greater speed, scale, and ability to tailor activity more efficiently. We see that in social engineering, where AI can make campaigns more targeted, and in technical work, where automation can compress parts of the attack process. The underlying methods often remain familiar. People, identities, exposed systems, and trusted access continue to feature prominently in the threat activity Microsoft observes.

AI is also becoming more connected to the systems and processes organizations already rely on. That brings another dimension to the security work.

Securing AI as part of the enterprise

Agents are a good example of these observations. They can interact with enterprise data, applications, APIs, and tools, with different levels of access and autonomy depending on how they are designed and deployed. Those connections are what allow agents to perform useful work, and they are also part of what security teams need to understand.

That makes it increasingly important to look at AI as part of a broader system. A model may be one component, but its security also depends on the data it can reach, the tools it can use, the identities and permissions involved, and the infrastructure and services around it.

The report looks at agent identity, appropriate access, authentication between agents, attribution, and the ability to revoke access. It also examines security considerations specific to AI, including prompt injection, memory, models and data, agent behavior, and the integrity of software and services around AI systems.

There is a lot we are still learning as these technologies develop. Security teams do have a strong foundation to build from. Identity and authorization, data protection, least privilege, monitoring, testing, and secure software development all remain relevant. AI puts those disciplines into new systems and increasingly connected workflows.

AI and vulnerability discovery

Advances in the application of AI toward code analysis are making it possible to examine software and identify weaknesses more effectively. That creates new opportunities to find vulnerabilities earlier and strengthen software before weaknesses are exploited. Those same advances can give threat actors more capable tools for vulnerability discovery and exploit development.

This is an important area to watch as capabilities develop. AI is giving defenders new ways to find and address weaknesses while giving cyberattackers new ways to look for them. The work on both sides continues to advance.

Connecting what defenders know

The same interconnectedness that shapes how activity moves across systems also shapes how defenders understand it. Security teams work with information from endpoints, identities, cloud environments, applications, email, networks, and threat intelligence. The report shows why those signals become more useful when they can be considered together. Threat activity spanning several systems may leave a pattern that no individual source shows on its own. In a more connected environment, the ability to relate activity across systems becomes an important part of understanding what is happening and where attention is needed.

The same principle extends beyond an individual organization. Trusted sharing of intelligence and information across organizations and public-private partnerships can connect pieces of activity that no one organization sees on its own.

AI can help with that work. Established techniques and repeatable tasks are increasingly candidates for automation, including bringing relevant information together and giving experienced defenders more capacity for deeper investigation.

The discussion of red teaming in this year’s report captures the balance well. Connecting known information and running established techniques can increasingly be automated. Finding an undocumented attack path, or recognizing how weaknesses that appear unrelated fit together, continues to benefit from experienced operators staying close to the work.

That balance will continue to evolve. There is substantial opportunity to use AI to help defenders work more effectively while preserving the human judgment, context, and expertise that remain essential to security work.

The 2026 Microsoft Digital Defense Report looks across the threat landscape, cybercrime, resilience, and the relationships among technologies, identities, systems, and people. Taken together, those findings give us a broader view of the increasingly interconnected environment security teams are responsible for understanding and protecting.

I encourage you to read the full report for a deeper look at the findings, data, and recommendations from Microsoft’s security and threat intelligence teams.

Read the 2026 Digital Defense Report for the full findings, data, and recommendations.

To learn more about Microsoft Security solutions, visit our website. Bookmark the Security blog to keep up with our expert coverage on security matters. Also, follow us on LinkedIn (Microsoft Security) and X (@MSFTSecurity) for the latest news and updates on cybersecurity.

The post Insights from the 2026 Microsoft Digital Defense Report  appeared first on Microsoft Security Blog.

Dwell time, the period between when an attacker gains access and when defenders detect and stop them, also increased this year across multiple sectors. While organizations responded faster once an intrusion was identified, detecting threats early remains a challenge. Attackers increasingly gain access through techniques that mimic legitimate activity, making malicious behavior harder to spot. For example, phishing accounted for 23% of observed intrusions in 2026, up from 7% in 2025, highlighting the continued importance of compromised identities as an entry point for broader attacks.

Taken together, the implication for governments is clear. Security in the AI era is no longer simply about preventing individual intrusions. It is about ensuring institutions can operate effectively in an environment where risks are interconnected, threats move faster, and attackers remain hidden longer. Public-private partnerships are also more important than ever for securing critical government infrastructure and developing the policies and regulations needed for emerging technologies.

In this year’s report, which examines cyber threat trends observed between July 2025 and June 2026, Terrell Cox, Microsoft’s Corporate Vice President & Deputy Chief Information Security Officer, and I explore how these dynamics are reshaping cyber risk. In a companion blog, Terrell takes a closer look at what these findings mean for CISOs and security professionals.

To strengthen resilience, governments should focus on five priorities:

1. Prepare for a faster threat environment
   AI is compressing the window for action. Adversaries are moving faster. A vulnerability’s discovery in the wild to active weaponization can be well below 24 hours. While the number of publicly disclosed software vulnerabilities (commonly tracked as CVEs) is projected to reach a record 72,000 in 2026.

Governments best prepared for the future will be those that can rapidly gather and assess information, make decisions, coordinate across institutions and industries, and communicate effectively during a crisis. This requires clearly defined responsibilities and trusted relationships established before an incident occurs, enabling swift and coordinated action when it matters most.

2. Build security into the AI ecosystem
   AI is becoming part of the infrastructure that governments, businesses, and citizens rely on every day. As governments continue to adopt AI across public services and encourage its broader use, they should approach its security as a resilience challenge rather than a narrow technical issue.

AI systems depend on interconnected infrastructure, data, models, applications, suppliers, and governance processes. Governments should promote security across this ecosystem through secure-by-design practices, testing and evaluation, stronger supply chain protections, transparency, accountability, and international cooperation on AI risk.

The goal is not to create a separate AI security agenda. It is to integrate AI security into broader efforts to protect critical infrastructure and build national resilience.

3. Plan for incidents to spread
   Governments may not immediately know whether an intrusion is criminal, geopolitical, or something else. Cybercriminals and nation-state actors pursue different objectives, but increasingly rely on many of the same entry points, including compromised identities, exposed applications, social engineering, and legitimate administrative tools.

Microsoft found that 52.2% of intrusions involving valid accounts resulted in additional credential theft, highlighting how quickly attackers can expand beyond an initial foothold. A seemingly isolated compromise can evolve into ransomware, espionage, data theft, or disruption of essential services.

Governments should therefore assess incidents not only by how they begin, but by where they could lead. Response plans should account for the suppliers, partners, and service providers supporting critical functions. As attacks expand beyond their initial targets, they can also cross organizational, sectoral, and national boundaries, reinforcing the need for global collaboration.

4. Enable timely, two-way public-private information sharing
   A compromised account at one organization may provide early warning of a broader campaign. Signals that appear inconclusive in isolation can reveal coordinated activity when combined across organizations and jurisdictions. Modern cybercrime operates through interconnected networks of actors, services, and infrastructure that no single institution can fully see or disrupt on its own.

Information sharing must be timely, trusted, and two-way—also known as bidirectional. The goal is not simply for companies to report threats to government. Public agencies should also return actionable intelligence, guidance, and warnings that help organizations protect their networks, customers, and operations. Trusted channels can enable this exchange among government agencies, law enforcement, critical infrastructure operators, technology providers, and international partners while respecting legal and privacy requirements.

Policymakers can support this cooperation through protections for good-faith information sharing, common anonymization standards, and investment in shared threat intelligence and detection capabilities. Information sharing should also lead to action, including investigations, disruption efforts, and accountability for those responsible for serious cyber intrusions.

5. Prepare essential services to operate through disruption
   The organizations governments depend on to deliver public services, including transportation systems, communications infrastructure, schools, universities, and critical infrastructure operators, are increasingly targeted by cyber threats. Resilience therefore requires understanding not only government systems, but the broader ecosystem that supports them.

Planning documents alone are not enough. Governments should regularly conduct tabletop exercises bringing together policymakers, operational leaders, law enforcement, critical infrastructure operators, and private-sector partners to test how they would respond to incidents disrupting essential services. These exercises can expose gaps in decision-making, information sharing, public communications, and cross-sector coordination before a real-world crisis. Microsoft’s work through initiatives such as the Advancing Regional Cybersecurity (ARC) program, most recently in Kenya, illustrates how scenario-based exercises and cross-sector collaboration can help strengthen preparedness and response capabilities across the broader ecosystem.

Government leaders should also know which services are most critical, which identities, systems, suppliers, and infrastructure support them, and how incidents will be escalated. Shared-service approaches can help extend security and response capabilities to local governments and public institutions that cannot build them independently.

As cyber incidents cross organizational and national boundaries, resilience depends not only on technical preparedness, but on whether institutions can coordinate effectively under pressure.

In an era of AI-enabled and increasingly interconnected cyber threats, resilience is no longer simply about recovering from an attack. It is about preparing for a world in which cyber incidents move faster, spread further, and affect more organizations than ever before. Governments best prepared for the future will be those that can contain harm, adapt quickly, and continue delivering critical services when citizens need them the most.

The post Preparing governments for an era of interconnected cyber risk appeared first on Microsoft Security Blog.

Here’s what’s new:

Extend protection and support investigations with Microsoft Defender

Bring more context into email investigation and hunting with Microsoft Security Copilot

Available for organizations using both Microsoft Defender and Microsoft Security Copilot, a new email detonation summary delivers AI-generated explanations of URL and file sandboxing results, helping SOC teams investigate faster by reducing the manual effort required to correlate detonation evidence and contextual signals.

Protect sensitive data in motion with Microsoft Purview and Microsoft Entra

Stop sensitive data from reaching shadow AI over the network

Now generally available, Microsoft Purview and Microsoft Entra Global Secure Access bring data security to the network across human actions and on-behalf-of (OBO) agentic traffic. Context-aware Microsoft Purview classification and policies are enforced by Entra at the network layer. Organizations can discover sensitive files and text in real time and block them from being shared to risky destinations. For example, if an employee or OBO agent tries to upload a sensitive document to an unsanctioned AI tool, the policy can stop the transfer before the data leaves.

Protect, investigate, and clean up enterprise data with Microsoft Purview

Manage labeling at enterprise scale with less administrative overhead

Microsoft Purview auto-labeling helps organizations automatically apply data security controls to sensitive content at enterprise scale. New auto-labeling enhancements improve policy scale, admin experience, and reporting. Policies now support simulations of up to 20 million items and up to 50,000 sites through adaptive scopes. Administrators can edit a policy without re-running simulation. New audit insights and reporting show policy coverage and processing activity. Together, these enhancements help organizations scale auto-labeling across larger environments with less administrative effort.

Investigate content created in Copilot apps such as Microsoft Loop, Copilot pages through established compliance processes

Microsoft Purview eDiscovery now supports search, hold, review, and export content in user-owned SharePoint embedded containers, to help streamline eDiscovery processes for legal, regulatory, and internal investigations. Investigators can find content from AI-powered experiences, including Microsoft Loop, Copilot Pages, Copilot Notebooks, and applications, such as Outlook newsletters, mapped to a user without requesting the container URL from a SharePoint administrator. An optional HTML conversion produces a more readable version for downstream legal tools, improving the review and export experience for experts.

Archive and permanently remove inactive content to improve AI readiness

With Microsoft Purview Data Lifecycle Management, administrators can now archive inactive SharePoint content without archiving the entire site. Archived content remains subject to retention and legal hold policies, and remains discoverable for eDiscovery, while dropping out of Microsoft 365 Copilot indexing (until reactivated). Organizations can also use Priority Cleanup to permanently delete approved content, including stale Teams recordings and transcripts, so it is no longer discoverable in eDiscovery, SharePoint search, or Microsoft 365 Copilot. Together, these capabilities help organizations meet compliance regulations, including those in highly regulated industries.

Advanced endpoint management extends to GCC High and DoD with Microsoft Intune

Bring modern endpoint management to regulated environments

Microsoft Intune Enterprise Application Management, Microsoft Cloud PKI, and Intune Remote Help are coming to Government Community Cloud with High security needs (GCC High), with Enterprise Application Management also being offered to organizations of the Department of Defense (DoD). These capabilities help government and defense organizations simplify application management, modernize certificate lifecycle management, resolve device issues faster, and reduce total cost of ownership, all while operating within their accredited cloud environment.

Stay in the Loop

Microsoft Security continually ships meaningful innovations across our portfolio, as well as research-driven insights and reports for the security community. In the Loop posts are your reliable source of what’s new across Microsoft Security and what it means for your security strategy. Check back for the next drop.

And join us at Microsoft Ignite, from November 17 to 20, 2026, in San Francisco or online, to see Microsoft Security innovations in action and go hands-on with the team that built it.

To learn more about Microsoft Security solutions, visit our website. Bookmark the Security blog to keep up with our expert coverage on security matters. Also, follow us on LinkedIn (Microsoft Security) and X (@MSFTSecurity) for the latest news and updates on cybersecurity.

The post ​​​​​​​​What’s new in Microsoft Security: September 2026​​ appeared first on Microsoft Security Blog.

Cyberattackers are using agents to automate execution at unprecedented scale. What once required entire teams now requires a single operator and an agent framework.

That shift has exposed a hard truth: security cannot operate at AI speed when protection and operations are built as separate systems. Every handoff, integration, and boundary slows defenders down. Agents inherit that complexity.

For agentic security to work, the industry needs a different model. It needs a modern cyber stack with the breadth to see across the environment and the depth to investigate and act. Security operations and native protection must function as one system. This is the integrated security operations center (ISOC).

Today we are announcing ISOC in Microsoft Defender: a foundation built for agentic security that brings leading solutions for security information and event management (SIEM) and threat protection together. It gives people and agents a shared foundation to see, understand, and act across the environment, without the complexity of operating separate systems.

Built for agentic security

In July 2026, we introduced the end-to-end cyber stack alongside Project Perception, with the focus of delivering the right models, a harness, and specialized agents to help defenders perceive, reason, and act at machine speed. But we are innovating at every layer of the stack, because intelligence and orchestration alone are not enough. Agents depend on the rest of the stack working as one.

They need signals and sensors that provide visibility, context that turns those signals into understanding, and actuators that translate decisions into protection. With ISOC, these layers work in unison, so agents can move beyond isolated tasks and help operate an agentic SOC.

Signals and sensors give the system awareness.

Context turns those signals into understanding.

Actuators turn insights into protective action.

ISOC brings these capabilities together as a foundation, so humans and agents can operate as one system, each contributing what they do best. Agents provide the speed and scale to execute continuously, while people set priorities, apply judgment, and define the outcomes that matter. Together, they empower defenders to keep pace with AI-powered threat actors and achieve better security outcomes.

Integrated protection loop

With ISOC enabling signals, context, and controls to work as one, it breaks the pattern of linear security workflows. The result is an integrated protection loop that continuously turns what defenders learn into stronger pre-breach protection.

Attack disruption in Microsoft Defender shows what this makes possible. Rich telemetry and controls enable the system to detect, predict, and adapt to an attacker while the attack is still unfolding. It disrupts threats in progress and anticipates where attackers may move next. It’s a protection loop that uses exposure insights to strengthen protection in near real-time with threat intelligence focusing the loop on the threats that matter most.

ISOC brings together the capabilities needed to make this loop native, eliminating the burden of assembling, tuning, and maintaining it yourself. And as protection advances, new capabilities can become part of that loop. The result is stronger protection and a different way of working, where practitioners spend less time chasing individual signals and more time applying judgment, setting priorities, and driving security outcomes.

Designed for the practitioner

For too long, practitioners have had to compensate for the boundaries in their security architecture, stitching together signals, rebuilding context, and moving between tools just to get the information and controls needed to act.

ISOC changes their starting point. The capabilities practitioners need to investigate, hunt, automate, manage incidents, understand threats, and take action are brought together and available by default. Instead of organizing their work around the boundaries between tools, teams can organize around the security outcome they are trying to achieve.

And that foundation gets more powerful as autonomy grows. The integrated protection loop can take on more of the continuous work of detecting and defending against threats, while agents help practitioners investigate, reason, and act using the same context and controls already available to them.

There’s no separate agentic layer to assemble or new operating model to stitch together. Practitioners can multiply their expertise where they already work, shifting more of their time from operating the security stack to directing the defense.

The path forward

Security has always been a race between attackers and defenders. AI changes the speed, scale, and economics of that race. The next SOC will not be defined by how many AI features it has, but by whether people and agents can perceive, reason, and act across an environment as one system.

Integrated security operations center (ISOC) in Microsoft Defender is available in preview today. Watch a recording of the full announcement or download the whitepaper: Agentic SOC: The new operating model for continuous defense.

To learn more about Microsoft Security solutions, visit our website. Bookmark the Security blog to keep up with our expert coverage on security matters. Also, follow us on LinkedIn (Microsoft Security) and X (@MSFTSecurity) for the latest news and updates on cybersecurity.

The post Reimagining the SOC for the agentic era in Microsoft Defender appeared first on Microsoft Security Blog.

Here’s what’s new:

Extend expert-led protection with new capabilities from Microsoft Defender Experts

Microsoft Defender Experts Threat Intelligence delivers expert-led threat intelligence and actionable insights tailored to your geography, industry, and risk profile to help security teams anticipate cyberthreats, assess risk, and take informed action. Microsoft Defender Experts MDR now covers third-party data sources ingested through Microsoft Sentinel. This extends around-the-clock managed detection and response and threat hunting to deliver protection across both Microsoft native and third-party data sources, including Palo Alto Networks, Amazon Web Services (AWS), Okta, and more. This coverage is available through Microsoft Defender Experts MDR P2.

Strengthen identity foundations for the AI era with Microsoft Entra

Microsoft Entra Tenant Governance brings an organization’s tenants into a single view to help address security gaps and blind spots. Centralized policies and cross-tenant delegated administration of multi-tenant environments help reduce shadow-tenant risk, configure policies, monitor configuration drift, and strengthen identity foundations for AI-powered operations.

Accelerate your move to cloud-native endpoint management with Microsoft Intune

Windows Autopilot device association lets admins link devices to their tenant and configure pre-enrollment experiences. Admins can optimize the out-of-box experience and rename devices, reducing onboarding friction.

Windows Unattended Support with Remote Sign-In allows IT and support staff to sign in to devices remotely, without involving the user. Role-based permissions, compliance checks, and session auditing are built in.

Speed up Microsoft Copilot readiness with scalable Microsoft Purview auto-labeling

Auto-labeling policies in Microsoft Purview now process up to 500,000 SharePoint and OneDrive files per day, up from 100,000. This increased limit helps organizations label and protect more content, extending data protection coverage. Because sensitivity labels help apply key security controls, including encryption and data loss prevention (DLP), organizations can extend data protection across more content and support their Microsoft 365 Copilot adoption efforts.

Contain agents with Microsoft Security Exposure Management

New Secure Now guidance for agentic containment helps organizations put controls in place before autonomous agent action expands across the environment. The recommendations focus on constraining agent-initiated actions that occur without explicit user approval, and hardening attack surfaces, limiting impact, governing identities and permissions, and increasing visibility across the environment.

Stay in the Loop

Microsoft Security is focused on delivering innovations across our portfolio, along with research-driven insights and reports for the security community. In the Loop posts are your reliable source of what’s new across Microsoft Security and what it means for your security strategy. Check back for the next drop.

To learn more about Microsoft Security solutions, visit our website. Bookmark the Security blog to keep up with our expert coverage on security matters. Also, follow us on LinkedIn (Microsoft Security) and X (@MSFTSecurity) for the latest news and updates on cybersecurity.

The post ​​​​​​What’s new in Microsoft Security: August 2026 appeared first on Microsoft Security Blog.

As organizations adopt cloud-native architectures at scale, protecting workloads requires more than scanning. Today, 82% of container users run Kubernetes in production, making runtime visibility and protection critical for modern applications.¹

That change, from scanning workloads to protecting them where they run, is exactly what Frost & Sullivan describes in its Frost Radar™: Cloud Workload Protection Platforms, 2026. Out of more than 45 qualified vendors, it benchmarked 20, and it found the category moving to a single runtime security model, one that ties together code, cloud, runtime, identity, and the security operations center (SOC).

Within that market, Frost & Sullivan names Microsoft a visionary leader, its category for vendors that balance innovation with growth and help set the direction of the market. Microsoft is also the largest cloud workload protection platform (CWPP) provider by revenue, with an estimated share of more than 22% of the global CWPP market. In the analyst’s words:

“Microsoft is positioned as a visionary leader in this analysis for its scale and breadth of [Microsoft] Defender for Cloud within a unified framework. The platform stands out for its breadth of coverage across infrastructure, workloads, identities, entitlements, data, and applications, and for its deep integration with Microsoft’s broader security ecosystem, allowing organizations to secure modern and AI-native application lifecycles, while reducing operational complexity.”

Scale and breadth, in one framework. That is what customers are asking for, and it is where this category is heading. 

Why cloud workload protection is being redefined

For a long time, protecting a workload meant scanning its image, fixing known vulnerabilities, and hardening configurations before deployment. That still matters. But it is no longer enough, because what looks safe before deployment can become exploitable once the workload is running.

Most teams are also dealing with real sprawl. A modern estate spans several clouds and mixes containers, Kubernetes, serverless functions, microservices, and AI workloads. Every layer throws off its own signals, and those signals rarely connect on their own. One misconfiguration looks harmless until it sits next to an over-permissioned identity and a container that is already live. Then it is a path into production.

The tools were not built for this. Posture sits in one console, workload scanning in another, detection in a third, and teams are left connecting them by hand, usually in the middle of an incident. What they need instead is one platform that can:

• Bring posture, runtime, identity, and control-plane signals into one place.
• Rank risk by what is truly exploitable, not by a severity score alone.
• Stop risky workloads close to deployment, before they reach production.
• Get what it finds at runtime to the developers and the SOC who can act on it.

The market is moving the same way. Frost & Sullivan expects CWPP spending to grow from $6.43 billion in 2025 to about $7.95 billion in 2026, and 19.1% a year through 2030. That is teams voting with their budgets to modernize cloud security, meet regulation, and protect the workloads behind their apps, data, and AI services.

What distinguishes leading platforms

Frost & Sullivan scores vendors on two things: how fast they innovate and how fast they grow. But the report is blunt about something more telling: the bar for leadership has moved. It is now, in the analyst’s words:

“Increasingly defined by runtime telemetry depth, container, and K8s security, workload behavior analysis, cloud-native threat detection, remediation and response automation, SOC integration, AI workload protection, and global go-to-market execution.”

Put plainly, discovery, scanning, and compliance checklists no longer separate the leaders. Depth at runtime does. The platforms pulling ahead tend to share a few traits:

• They cover real ground, from infrastructure and workloads to identities, data, and applications, without asking you to bolt five products together.
• They go deep at runtime, not just posture and log review.
• They carry cloud detection and response (CDR) straight into the SOC.
• They connect code, cloud, and the SOC instead of treating each as its own island.
• They span clouds with both agent and agentless coverage, and they are moving quickly on AI and data security.

None of that is about longer findings lists. It is about context: seeing how the pieces connect and acting on the few that matter.

How Microsoft helps organizations protect cloud workloads

Microsoft’s capabilities address the problems customers raise most, and Frost & Sullivan points to the same strengths: 

“The strength in scaled runtime protection depth, strong CDR expansion, and ability to operationalize cloud runtime security across [Microsoft] Defender XDR, [Microsoft] Sentinel, GitHub, [Microsoft] Security Copilot, and the broader Microsoft security stack give Microsoft clearest advantages, particularly for large enterprises that already operate across Microsoft security, Azure infrastructure, GitHub, and Sentinel environments.”

Here is what that looks like in practice, starting from the problem in each case. 

1. Protect workloads while they are running

Microsoft Defender for Cloud watches workloads while they run. A lightweight sensor (eBPF-based) picks up Kubernetes events, process activity, and network traffic, and detections map to MITRE ATT&CK, so alerts line up with real cyberattacker behavior. Most of the recent effort has gone into the container layer: DNS detection for Kubernetes on Azure AKS, Amazon EKS, and Google GKE; anti-malware that blocks rather than just alerts; runtime protection for EKS Bottlerocket; and drift blocking when a binary changes mid-run.

Defender for Cloud can also act before a workload starts. Kubernetes’ gating applies policy at the cluster and namespace level, so a risky or non-compliant image is blocked before it ever starts. Frost & Sullivan calls this out as especially relevant to CWPP, because it puts preventive controls right next to production. That is the whole idea: catch a bad image before it becomes an incident, not after.

2. Get runtime signal to the SOC

Runtime signal only helps if it reaches the people who respond. With expanded CDR, Defender for Cloud ties runtime telemetry, Kubernetes audit data, process and network activity, control-plane events, and identity signals to specific workload incidents, then hands them to Microsoft Defender XDR and Microsoft Sentinel. A suspicious process in a running cluster does not land as a lonely alert. It arrives already connected to the identity that launched it and the activity around it.

For the SOC, that means faster answers and far less stitching signals together by hand.

3. Send runtime findings back to the developers who can fix them

Finding a problem at runtime is only half the work. Someone still has to fix it. Defender for Cloud links runtime context, exploitability, and attack-path detail to developer workflows through GitHub Advanced Security and Copilot Autofix, syncing both ways between security and development. A risk caught in production can go straight to the engineer who owns the code, get fixed at the source, and be checked afterward.

The right issue reaches the right owner, and security and DevOps finally work from the same list.

4. Extend protection to AI and across clouds

More and more, the workloads worth protecting are AI. Defender for Cloud supports model scanning and threat protection, including prompt injection and suspicious access, for Azure AI Foundry and Azure OpenAI, and AI security posture management for Google Vertex AI and Amazon Bedrock. It spans Microsoft Azure, Amazon Web Services (AWS), Google Cloud Platform (GCP), and hybrid environments with both agent and agentless coverage, and Microsoft Security Copilot adds guided investigation across the workflow.

Protection follows the workload, whether that is a new AI service or a third cloud.

What this signals for security leaders

For anyone choosing a workload protection platform this year, the shift in this report changes the questions worth asking. The ones to put at the top:

• Is workload protection part of one cloud security platform, or a separate tool wired onto the SOC after the fact?
• Can it stop a risky workload before production, or only flag it afterward?
• Does it connect runtime activity to identity, data, and control-plane context, and rank what is genuinely exploitable?
• Do its findings reach both the SOC and the developers who can act on them?
• Does it hold up across several clouds and AI workloads?

The vendors that can answer “yes” are the ones shaping what comes next, and the Frost Radar places Microsoft among them.

Bottom line

Frost & Sullivan’s Frost Radar™: Cloud Workload Protection Platforms, 2026 reinforces a clear shift. Cloud workload protection is leaving isolated scanning behind for runtime security that connects posture, identity, code, and the SOC. Frost & Sullivan positions Microsoft as a visionary leader, and the largest CWPP provider by revenue, because Defender for Cloud brings that range together in one framework, goes deep at runtime and in CDR, and plugs into the wider Microsoft security stack.

Learn more

• Read Frost & Sullivan’s Frost Radar™: Cloud Workload Protection Platforms, 2026 to see how leading vendors are evaluated and how the category is shifting toward unified cloud runtime security. 
• Explore Microsoft cloud security solutions to see how unified posture management, risk prioritization, and protection across cloud and AI can help reduce risk.

To learn more about Microsoft Security solutions, visit our website. Bookmark the Security blog to keep up with our expert coverage on security matters. Also, follow us on LinkedIn (Microsoft Security) and X (@MSFTSecurity) for the latest news and updates on cybersecurity.

¹Kubernetes Established as the De Facto ‘Operating System’ for AI as Production Use Hits 82% in 2025 CNCF Annual Cloud Native Survey. PR Newswire, January 20, 2026.

The post Microsoft named a Leader in the Frost Radar™: Cloud Workload Protection Platforms, 2026 appeared first on Microsoft Security Blog.

We are excited to announce that we have been named a Leader in the 2026 IDC MarketScape: Worldwide MDR/MXDR for the Enterprise Vendor Assessment (Doc #US54792426, July 2026). Read the excerpt here.

Expert-led MDR, built on the Microsoft Defender platform

Microsoft Defender Experts MDR is a round-the-clock, expert-led managed detection and response service that helps security teams triage, investigate, and respond to incidents so they can stop cyberattackers in their tracks and prevent future compromise. Rather than bolting a separate stack of tools and connectors onto your environment, the service operates natively on Microsoft Defender, with built-in protection across endpoints, identities, email, cloud apps, cloud workloads, and network security, as well as around-the-clock proactive threat hunting with Microsoft Defender Experts Hunting.

Because the service is delivered on the same platform it monitors, detection and intelligence improvements reach customers continuously. The insights our experts generate also strengthen protection across the broader Defender ecosystem, so every customer benefits from what we learn defending the next environment.

Threat intelligence at internet scale

Great detection starts with great intelligence. Defender Experts MDR draws on Microsoft’s global threat intelligence: more than 10,000 security researchers and 100 trillion signals analyzed every day across billions of users and millions of organizations.¹ That breadth lets our analysts recognize subtle patterns early, often before a campaign escalates, and respond with higher-confidence attribution than intelligence sourced from any single customer’s telemetry could provide.

AI-accelerated operations, expert-led decisions

Defender Experts MDR also combines advanced AI and generative AI with seasoned human experts. AI filters noise, grades and classifies incidents, and accelerates investigation at machine speed and scale, while our analysts own the outcome. According to the IDC MarketScape, “70% AI-assisted workflows are enabled through automated noise filtering, AI-based grading, and agentic operations while maintaining expert decision-making.” Furthermore, “quantified outcomes noted include 97% AI classification accuracy, 77% malware/phishing agent-investigated, 72% faster resolution combining AI and humans, and 45% autonomous investigations.”

The impact shows up in the work. Over the past year, Defender Experts mitigated 27,000 high-severity incidents, and the team’s threat research now contributes a meaningful share of all Defender detections, enriching protection for customers well beyond the MDR service itself. Throughout, a dedicated security delivery expert and on-demand access to our experts keep customers informed with proactive check-ins, live dashboards, and clear, actionable reporting.

Managed threat hunting, included

Many providers treat proactive threat hunting as a premium add-on. Defender Experts MDR includes it as a core part of the service with Defender Experts Hunting, extending your team with Microsoft experts who continuously look for advanced threats across your environment. These hunts are informed by Microsoft Threat Intelligence, Defender telemetry, and human analysis, in order to better identify malicious activity and improve security operations center (SOC) response.

When a threat is found, Defender Expert notifications appear as incidents in the Defender portal with technical context, recommended remediation, and, when needed, access to on-demand support for additional guidance. The work also feeds back into hunter-trained AI and reporting, so customers can see what was investigated, how the activity maps to MITRE tactics, and how threats are categorized by behavior, characteristics, and impact.

Get started

Read the IDC MarketScape: Worldwide MDR/MXDR for the Enterprise 2026 Vendor Assessment excerpt, and visit the Microsoft Defender Experts MDR webpage to see how expert-led, round-the-clock managed detection and response can extend your team, drive SOC efficiency, and help you stay ahead of emerging cyberthreats.

To learn more about Microsoft Security solutions, visit our website. Bookmark the Security blog to keep up with our expert coverage on security matters, and follow us on LinkedIn (Microsoft Security) and X (@MSFTSecurity) for the latest news and updates on cybersecurity.

¹Microsoft Digital Defense Report 2025.

The post Microsoft named a Leader in the 2026 IDC MarketScape for MDR/MXDR for the Enterprise  appeared first on Microsoft Security Blog.

Modern IT estates now span multiple clouds and on-premises systems, with architectures built on containers, Kubernetes, serverless functions, microservices, APIs, and AI-powered workloads. This increases both the volume and the interconnectedness of security signals. The challenge is no longer identifying individual risks, but determining how misconfigurations, identities, and data exposures combine to create real attack paths, and which of these are most critical to fix at the source. 

KuppingerCole’s Leadership Compass: Cloud Native Application Protection Platforms (CNAPP) reflects this shift. The report describes how CNAPP is evolving from a consolidation of cloud security tools into the security foundation for AI-native enterprises, combining cloud security, AI security posture management, runtime protection, attack path analysis, cloud detection and response, and agentic AI operations into unified platforms.

Within this evolving market, KuppingerCole names Microsoft a Leader across all four of its Leadership categories: Overall, Product, Innovation, and Market. In the report’s words: 

“Microsoft earns its Overall Leadership with its Defender for Cloud that is redefining the CNAPP market by extending cloud security beyond infrastructure protection and into a unified security platform for cloud, data, identity, AI, and security operations, supported by one of the industry’s most advanced agentic AI ecosystems.” 

That recognition reflects where the category is heading: toward platforms that unify cloud and AI security into one operational view of risk. 

Why CNAPP is being redefined 

KuppingerCole makes a clear point: CNAPP is no longer about posture or visibility alone. It is becoming the operational foundation for securing AI-powered applications, services, and business processes, across the full software lifecycle from cloud infrastructure to the AI systems running on top of it.

Modern environments introduce complexity across: 

• Multicloud and hybrid infrastructure. 
• Rapid development and continuous deployment. 
• Containers, serverless, microservices, and APIs. 
• AI models, agents, pipelines, and machine identities. 

This complexity exposes the limits of traditional, siloed tools, where cloud posture, workload protection, AI security, and the security operations center (SOC) each live in their own console. Organizations now need platforms that can: 

• Correlate posture, runtime, identity, data, application, and AI signals. 
• Prioritize risk based on exploitability, not severity alone. 
• Integrate security across development, cloud operations, and the SOC. 
• Bring AI systems into the same risk model as the rest of the cloud. 

Runtime intelligence is now central to this shift. Across the platforms KuppingerCole evaluated, 94% detect active exploitation of the complex attack paths they surface, moving teams from long lists of findings to the exposures threat actors can actually use. 

What distinguishes leading platforms 

KuppingerCole evaluates providers on product strength, innovation, and market presence, and, more importantly, on how effectively they help organizations manage real risk across cloud and AI. Several themes define the next generation of platforms: 

• AI security posture management that governs models, pipelines, and AI-specific attack paths. 
• Agentic AI that investigates, validates exposures, and helps remediate, not just detect. 
• Runtime-driven risk prioritization focused on what is exploitable in production. 
• Security graphs and attack path analysis across identity, data, network, workload, and AI. 
• Convergence of CNAPP with cloud detection and response, integrated with the SOC. 

Taken together, these capabilities represent a move from fragmented visibility to connected, contextual risk management that spans cloud and AI in a single fabric. 

How Microsoft helps organizations manage real risk 

1. Connect cross-domain signals to prioritize real attack paths 

Most security tools surface large volumes of findings, but isolated findings do not reflect how cyberattacks actually happen. Microsoft Defender for Cloud uses the Cloud Security Graph and risk-based, multicloud attack path analysis to correlate posture, identity (human and non-human), data, network, and workload signals and identify which risks are truly exploitable. A misconfigured storage resource may look low priority on its own. Exposed to the internet, combined with excessive permissions, and connected to sensitive data, it becomes part of a clear attack path.  

What this means: Security teams can prioritize real attack paths instead of individual findings, helping reduce alert fatigue and improve remediation speed and precision.  

2. Secure AI as part of cloud risk, and use AI to run security 

Defender for Cloud brings AI security posture management into the same model as the rest of the cloud, helping organizations validate AI deployment configurations, access controls, model provenance, approved model usage, and identify potential shadow AI risks within supported environments. Through Microsoft Security Copilot and a growing set of specialized security agents, the platform also helps teams investigate, prioritize, guide remediation, and automate workflows.  

What this means: Organizations can govern AI as part of cloud risk rather than in a separate silo, and shift AI from flagging risk to actively helping resolve it. 

3. Reduce complexity from code to cloud to SOC 

As environments scale, fragmented tools make it difficult to understand how risks connect and where to focus first. Defender for Cloud connects code and infrastructure definitions, assesses cloud configurations, protect workloads at runtime, monitor applications and APIs, govern identities, correlate threats across the broader digital estate, and use AI to accelerate investigation and remediation across multicloud and hybrid environments. 

What this means: Security teams can investigate faster, prioritize more consistently, and respond more quickly across fragmented cloud and application environments. 

What this signals for security leaders 

The Leadership Compass offers a signal for where cloud security is headed: toward platforms that connect context across cloud, application, and AI environments so teams can prioritize the risks most likely to be exploited and reduce exposure faster. Security leaders should now ask: 

• Can the platform correlate signals across identity, endpoints, data, cloud, runtime, and applications? 
• Does it see AI models, agents, and pipelines as part of cloud risk, or is AI a separate tool? 
• Can it prioritize risk based on exploitability, not just severity? 
• Does AI help the team investigate and remediate, or only detect? 
• Can it scale across multicloud and AI environments and reach into the SOC? 

These are the capabilities that define the next generation of cloud-native application protection. 

Bottom line 

KuppingerCole’s 2026 CNAPP Leadership Compass reinforces a clear shift: CNAPP is becoming the control plane for managing risk across cloud, identity, data, applications, and AI. Microsoft’s recognition as a Leader across all four Leadership categories reflects this shift, bringing posture, runtime, identity, data, application, and AI signals into a connected platform that helps organizations prioritize and reduce risk continuously.  

Learn more 

• Read KuppingerCole’s Leadership Compass: Cloud Native Application Protection Platforms (CNAPP)  to see how leading vendors are evaluated and how the category is shifting toward securing the AI-native enterprise. 
• Explore Microsoft cloud security solutions to see how unified posture management, risk prioritization, and protection across cloud and AI can help reduce risk. 

To learn more about Microsoft Security solutions, visit our website. Bookmark the Security blog to keep up with our expert coverage on security matters. Also, follow us on LinkedIn (Microsoft Security) and X (@MSFTSecurity) for the latest news and updates on cybersecurity.

The post ​​Microsoft named a Leader in the KuppingerCole Leadership Compass for Cloud Native Application Protection Platforms (CNAPP) appeared first on Microsoft Security Blog.