{"id":966111,"date":"2023-09-07T02:35:09","date_gmt":"2023-09-07T09:35:09","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&p=966111"},"modified":"2024-08-02T00:24:24","modified_gmt":"2024-08-02T07:24:24","slug":"sigma-secure-gpt-inference-with-function-secret-sharing","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/sigma-secure-gpt-inference-with-function-secret-sharing\/","title":{"rendered":"SIGMA: Secure GPT Inference with Function Secret Sharing"},"content":{"rendered":"

Secure 2-party computation (2PC) enables secure inference that offers protection for both proprietary machine learning (ML) models and sensitive inputs to them. However, the existing secure inference solutions suffer from high latency and communication overheads, particularly for transformers. Function secret sharing (FSS) is a recent paradigm for obtaining efficient 2PC protocols with a preprocessing phase. We provide SIGMA, the first end-to-end system for secure transformer inference based on FSS. By constructing new FSS-based protocols for complex machine learning functionalities, such as Softmax and GeLU, and also accelerating their computation on GPUs, SIGMA improves the latency of secure inference of transformers by 11-19x<\/mn><\/mo><\/math>over the state-of-the-art that uses preprocessing and GPUs. We present the first secure inference of generative pre-trained transformer (GPT) models. In particular, SIGMA executes GPT-Neo with 1.3 billion parameters in 7.4s and HuggingFace’s GPT2 in 1.6s.<\/p>\n","protected":false},"excerpt":{"rendered":"

Secure 2-party computation (2PC) enables secure inference that offers protection for both proprietary machine learning (ML) models and sensitive inputs to them. However, the existing secure inference solutions suffer from high latency and communication overheads, particularly for transformers. Function secret sharing (FSS) is a recent paradigm for obtaining efficient 2PC protocols with a preprocessing phase. […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13558],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[246691],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-966111","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-security-privacy-cryptography","msr-locale-en_us","msr-field-of-study-computer-science"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2024-6-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/eprint.iacr.org\/2023\/1269","label_id":"243109","label":0}],"msr_related_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/eprint.iacr.org\/2023\/1269.pdf","label_id":"243112","label":0}],"msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Kanav Gupta","user_id":0,"rest_url":false},{"type":"text","value":"Neha Jawalkar","user_id":0,"rest_url":false},{"type":"text","value":"Ananta Mukherjee","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Nishanth Chandran","user_id":33084,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Nishanth Chandran"},{"type":"user_nicename","value":"Divya Gupta","user_id":37766,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Divya Gupta"},{"type":"user_nicename","value":"Ashish Panwar","user_id":42153,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ashish Panwar"},{"type":"user_nicename","value":"Rahul Sharma","user_id":36308,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Rahul Sharma"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[507611],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":507611,"post_title":"EzPC (Easy Secure Multi-party Computation)","post_name":"ezpc-easy-secure-multi-party-computation","post_type":"msr-project","post_date":"2018-10-10 01:30:32","post_modified":"2023-09-07 08:59:53","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/ezpc-easy-secure-multi-party-computation\/","post_excerpt":"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 Multi-Party Computation (MPC), provides an answer to this seemingly impossible task using sophisticated mathematical protocols. However, two big challenges remain:…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/507611"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/966111"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":6,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/966111\/revisions"}],"predecessor-version":[{"id":1064343,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/966111\/revisions\/1064343"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=966111"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=966111"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=966111"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=966111"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=966111"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=966111"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=966111"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=966111"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=966111"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=966111"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=966111"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=966111"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=966111"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=966111"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=966111"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=966111"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}