{"id":507611,"date":"2018-10-10T01:30:32","date_gmt":"2018-10-10T08:30:32","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&p=507611"},"modified":"2023-09-07T08:59:53","modified_gmt":"2023-09-07T15:59:53","slug":"ezpc-easy-secure-multi-party-computation","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/ezpc-easy-secure-multi-party-computation\/","title":{"rendered":"EzPC (Easy Secure Multi-party Computation)"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t\"EzPC\t\t<\/div>\n\t\t\n\t\t
\n\t\t\t\n\t\t\t
\n\t\t\t\t\n\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n

EzPC (Easy Secure Multi-party Computation)<\/h1>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n

Consider the following scenario: two hospitals, each having sensitive patient data, must compute statistical information about their joint data. Privacy regulations forbid them from sharing data in the clear with any entity. So, can they compute this information while keeping their private data encrypted (or \u201chidden\u201d) from each other?<\/p>\n\n\n\n

Cryptography and specifically, the primitive Secure Multi-Party Computation (MPC), provides an answer to this seemingly impossible task using sophisticated mathematical protocols. However, two big challenges remain:<\/p>\n\n\n\n

    \n
  1. Until recently, these cryptographic protocols have only been efficiently executable for simpler functions such as aggregations, linear regressions and so on; while, ideally one would like to execute more complex AI algorithms that could allow the hospitals to learn and predict diseases or health abnormalities.<\/li>\n\n\n\n
  2. Secondly, to execute these protocols, one must express the computation at the low-level of circuits comprising of AND and OR gates, which is both highly cumbersome and inefficient.<\/li>\n<\/ol>\n\n\n\n

    The EzPC (or Easy Secure Multi-Party Computation) project at MSR India addresses both these issues:<\/p>\n\n\n\n

      \n
    1. We have developed a system, CrypTFlow (opens in new tab)<\/span><\/a>, that takes as input TensorFlow (or ONNX) inference code and automatically compiles it into an efficient secure computation protocol for the same code.<\/li>\n\n\n\n
    2. To serve as a backend to our compiler, we have developed new secure multi-party computation protocols for computing various neural network training and prediction algorithms that have orders of magnitude improvement in performance over prior state-of-the-art.<\/li>\n<\/ol>\n\n\n\n

      To learn more about how developers can build scalable and efficient MPC protocols for secure inference tasks with absolutely no cryptography expertise using the CrypTFlow system, visit this blog post<\/a>. For more information, contact the team at ezpc@microsoft.com<\/a><\/p>\n\n\n","protected":false},"excerpt":{"rendered":"

      Consider the following scenario: two hospitals, each having sensitive patient data, must compute statistical information about their joint data. Privacy regulations forbid them from sharing data in the clear with any entity. So, can they compute this information while keeping their private data encrypted (or \u201chidden\u201d) from each other? Cryptography and specifically, the primitive Secure […]<\/p>\n","protected":false},"featured_media":811219,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13560,13558],"msr-locale":[268875],"msr-impact-theme":[261673],"msr-pillar":[],"class_list":["post-507611","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-programming-languages-software-engineering","msr-research-area-security-privacy-cryptography","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[507662,507653,950796,720217,951414,727696,966111,744307,1064340,764191,789491,790529,810385,838957,611136,854733,685314,950790,710251],"related-downloads":[569946],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Nishanth Chandran","user_id":33084,"people_section":"Section name 1","alias":"nichandr"},{"type":"user_nicename","display_name":"Divya Gupta","user_id":37766,"people_section":"Section name 1","alias":"digup"},{"type":"user_nicename","display_name":"Aseem Rastogi","user_id":36021,"people_section":"Section name 1","alias":"aseemr"},{"type":"user_nicename","display_name":"Rahul Sharma","user_id":36308,"people_section":"Section name 1","alias":"rahsha"},{"type":"user_nicename","display_name":"Ashish Panwar","user_id":42153,"people_section":"Section name 1","alias":"ashishpanwar"},{"type":"user_nicename","display_name":"Kashish Mittal","user_id":41374,"people_section":"Section name 1","alias":"kmittal"}],"msr_research_lab":[199562],"msr_impact_theme":["Health"],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/507611"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":13,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/507611\/revisions"}],"predecessor-version":[{"id":966195,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/507611\/revisions\/966195"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/811219"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=507611"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=507611"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=507611"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=507611"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=507611"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}