{"id":90341,"date":"2019-12-13T09:00:40","date_gmt":"2019-12-13T17:00:40","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/\/?p=90341"},"modified":"2023-05-15T23:01:34","modified_gmt":"2023-05-16T06:01:34","slug":"finding-a-common-language-to-describe-ai-security-threats","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/","title":{"rendered":"Finding a common language to describe AI security threats"},"content":{"rendered":"<p>As artificial intelligence (AI) and machine learning systems become increasingly important to our lives, it\u2019s critical that when they fail we understand how and why. Many research papers have been dedicated to this topic, but inconsistent vocabulary has limited their usefulness. In collaboration with Harvard University\u2019s\u00a0<a href=\"https:\/\/cyber.harvard.edu\/\" target=\"_blank\" rel=\"noopener noreferrer\">Berkman Klein Center<\/a>, Microsoft published a series of materials that define common vocabulary that can be used to describe intentional and unintentional failures.<\/p>\n<p>Read <a href=\"https:\/\/blogs.microsoft.com\/on-the-issues\/2019\/12\/06\/ai-machine-learning-security\/\" target=\"_blank\" rel=\"noopener noreferrer\">Solving the challenge of securing AI and machine learning systems<\/a> to learn more about Microsoft\u2019s AI taxonomy papers.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Microsoft published a series of materials that define common vocabulary that can be used to describe intentional and unintentional failures.<\/p>\n","protected":false},"author":96,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ms_queue_force_push":false,"ms_queue_id":"","ep_exclude_from_search":false,"_classifai_error":"","_classifai_text_to_speech_error":"","footnotes":""},"content-type":[3659],"topic":[3664],"products":[],"threat-intelligence":[],"tags":[3822,3809],"coauthors":[1916],"class_list":["post-90341","post","type-post","status-publish","format-standard","hentry","content-type-best-practices","topic-ai-and-machine-learning","tag-microsoft-security-insights","tag-security-strategies"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v24.2 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Finding a common language to describe AI security threats<\/title>\n<meta name=\"description\" content=\"Microsoft published a series of materials that define common vocabulary that can be used to describe intentional and unintentional failures.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Finding a common language to describe AI security threats\" \/>\n<meta property=\"og:description\" content=\"Microsoft published a series of materials that define common vocabulary that can be used to describe intentional and unintentional failures.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/\" \/>\n<meta property=\"og:site_name\" content=\"Microsoft Security Blog\" \/>\n<meta property=\"article:published_time\" content=\"2019-12-13T17:00:40+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-05-16T06:01:34+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-content\/uploads\/2018\/08\/cropped-microsoft_logo_element.png\" \/>\n\t<meta property=\"og:image:width\" content=\"512\" \/>\n\t<meta property=\"og:image:height\" content=\"512\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Microsoft Security Team\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Microsoft Security Team\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"&lt;1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/\"},\"author\":[{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/author\/microsoft-secure-blog-staff\/\",\"@type\":\"Person\",\"@name\":\"Microsoft Security Team\"}],\"headline\":\"Finding a common language to describe AI security threats\",\"datePublished\":\"2019-12-13T17:00:40+00:00\",\"dateModified\":\"2023-05-16T06:01:34+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/\"},\"wordCount\":100,\"publisher\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#organization\"},\"keywords\":[\"Microsoft Security Insights\",\"Security strategies\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/\",\"name\":\"Finding a common language to describe AI security threats\",\"isPartOf\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#website\"},\"datePublished\":\"2019-12-13T17:00:40+00:00\",\"dateModified\":\"2023-05-16T06:01:34+00:00\",\"description\":\"Microsoft published a series of materials that define common vocabulary that can be used to describe intentional and unintentional failures.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Finding a common language to describe AI security threats\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#website\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/\",\"name\":\"Microsoft Security Blog\",\"description\":\"Expert coverage of cybersecurity topics\",\"publisher\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#organization\",\"name\":\"Microsoft Security Blog\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-content\/uploads\/2018\/08\/cropped-cropped-microsoft_logo_element.png\",\"contentUrl\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-content\/uploads\/2018\/08\/cropped-cropped-microsoft_logo_element.png\",\"width\":512,\"height\":512,\"caption\":\"Microsoft Security Blog\"},\"image\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#\/schema\/logo\/image\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Finding a common language to describe AI security threats","description":"Microsoft published a series of materials that define common vocabulary that can be used to describe intentional and unintentional failures.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/","og_locale":"en_US","og_type":"article","og_title":"Finding a common language to describe AI security threats","og_description":"Microsoft published a series of materials that define common vocabulary that can be used to describe intentional and unintentional failures.","og_url":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/","og_site_name":"Microsoft Security Blog","article_published_time":"2019-12-13T17:00:40+00:00","article_modified_time":"2023-05-16T06:01:34+00:00","og_image":[{"width":512,"height":512,"url":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-content\/uploads\/2018\/08\/cropped-microsoft_logo_element.png","type":"image\/png"}],"author":"Microsoft Security Team","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Microsoft Security Team","Est. reading time":"<1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/#article","isPartOf":{"@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/"},"author":[{"@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/author\/microsoft-secure-blog-staff\/","@type":"Person","@name":"Microsoft Security Team"}],"headline":"Finding a common language to describe AI security threats","datePublished":"2019-12-13T17:00:40+00:00","dateModified":"2023-05-16T06:01:34+00:00","mainEntityOfPage":{"@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/"},"wordCount":100,"publisher":{"@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#organization"},"keywords":["Microsoft Security Insights","Security strategies"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/","url":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/","name":"Finding a common language to describe AI security threats","isPartOf":{"@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#website"},"datePublished":"2019-12-13T17:00:40+00:00","dateModified":"2023-05-16T06:01:34+00:00","description":"Microsoft published a series of materials that define common vocabulary that can be used to describe intentional and unintentional failures.","breadcrumb":{"@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2019\/12\/13\/finding-a-common-language-to-describe-ai-security-threats\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/"},{"@type":"ListItem","position":2,"name":"Finding a common language to describe AI security threats"}]},{"@type":"WebSite","@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#website","url":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/","name":"Microsoft Security Blog","description":"Expert coverage of cybersecurity topics","publisher":{"@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#organization","name":"Microsoft Security Blog","url":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-content\/uploads\/2018\/08\/cropped-cropped-microsoft_logo_element.png","contentUrl":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-content\/uploads\/2018\/08\/cropped-cropped-microsoft_logo_element.png","width":512,"height":512,"caption":"Microsoft Security Blog"},"image":{"@id":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/#\/schema\/logo\/image\/"}}]}},"msxcm_display_generated_audio":false,"distributor_meta":false,"distributor_terms":false,"distributor_media":false,"distributor_original_site_name":"Microsoft Security Blog","distributor_original_site_url":"https:\/\/www.microsoft.com\/en-us\/security\/blog","push-errors":false,"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/posts\/90341","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/users\/96"}],"replies":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/comments?post=90341"}],"version-history":[{"count":0,"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/posts\/90341\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/media?parent=90341"}],"wp:term":[{"taxonomy":"content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/content-type?post=90341"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/topic?post=90341"},{"taxonomy":"products","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/products?post=90341"},{"taxonomy":"threat-intelligence","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/threat-intelligence?post=90341"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/tags?post=90341"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/security\/blog\/wp-json\/wp\/v2\/coauthors?post=90341"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}