{"id":214197,"date":"2026-02-16T15:12:00","date_gmt":"2026-02-16T20:12:00","guid":{"rendered":"https:\/\/news-you-need.com\/index.php\/2026\/02\/16\/ndss-2025-siguard-guarding-secure-inference-with-post-data-privacy\/"},"modified":"2026-02-16T15:25:09","modified_gmt":"2026-02-16T20:25:09","slug":"ndss-2025-siguard-guarding-secure-inference-with-post-data-privacy","status":"publish","type":"post","link":"https:\/\/news-you-need.com\/index.php\/2026\/02\/16\/ndss-2025-siguard-guarding-secure-inference-with-post-data-privacy\/","title":{"rendered":"NDSS 2025 &#8211; SiGuard: Guarding Secure Inference With Post Data Privacy"},"content":{"rendered":"<p><a href=\"https:\/\/securityboulevard.com\/2026\/02\/ndss-2025-siguard-guarding-secure-inference-with-post-data-privacy\/\">NDSS 2025 &#8211; SiGuard: Guarding Secure Inference With Post Data Privacy<\/a><\/p>\n<p><a href=\"https:\/\/securityboulevard.com\/2026\/02\/ndss-2025-siguard-guarding-secure-inference-with-post-data-privacy\/\">https:\/\/securityboulevard.com\/2026\/02\/ndss-2025-siguard-guarding-secure-inference-with-post-data-privacy\/<\/a><\/p>\n<p>Publish Date: <a href=\"publish_date]\">2026-02-16 15:12:00<\/a><\/p>\n<p>Source Domain: <a href=\"securityboulevard.com\">securityboulevard.com<\/a><\/p>\n<p>Session 12C: Membership Inference <\/p>\n<p><iframe loading=\"lazy\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen=\"\" src=\"https:\/\/www.youtube-nocookie.com\/embed\/bK8TQv3JTJE?si=FIq0mnZ-plegHH5W\" width=\"560\" frameborder=\"0\" data-preserve-html-node=\"true\" title=\"YouTube video player\" height=\"315\"><\/iframe><br \/>\nAuthors, Creators &#038; Presenters: Xinqian Wang (RMIT University), Xiaoning Liu (RMIT University), Shangqi Lai (CSIRO Data61), Xun Yi (RMIT University), Xingliang Yuan (University of Melbourne)<br \/>\nPAPER<br \/>SIGuard: Guarding Secure Inference with Post Data Privacy<br \/>\nSecure inference is designed to enable encrypted machine learning model prediction over encrypted data. It will ease privacy concerns when models are deployed in Machine Learning as a Service (MLaaS). For efficiency, most of recent secure inference protocols are constructed using secure multi-party computation (MPC) techniques. They can ensure that MLaaS computes inference without knowing the inputs of users and model owners. However, MPC-based protocols do not hide information revealed from their output. In the context of secure inference, prediction outputs (i.e., inference results of encrypted user inputs) are revealed to the users. As a result, adversaries can compromise output privacy of secure inference, i.e., launching Membership Inference Attacks (MIAs) by querying encrypted models, just like MIAs in plaintext inference. We observe that MPC-based secure inference often yields perturbed predictions due to approximations of nonlinear functions like softmax compared to its plaintext version on identical user inputs. Thus, we evaluate whether or not MIAs can still exploit such perturbed predictions on known secure inference protocols. Our results show that secure inference remains vulnerable to MIAs. The adversary can steal membership information with high successful rates comparable to plaintext MIAs. To tackle this open challenge, we propose SIGuard, a framework to guard the output privacy of secure inference from being exploited by MIAs. SIGuard\u2019s protocol can seamlessly be integrated into existing MPC-based secure inference protocols without intruding on their computation. It proceeds with encrypted predictions outputted from secure inference, and then crafts&#8230;<br \/>\n<br \/><a href=\"https:\/\/securityboulevard.com\/2026\/02\/ndss-2025-siguard-guarding-secure-inference-with-post-data-privacy\/\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>NDSS 2025 &#8211; SiGuard: Guarding Secure Inference With Post Data Privacy https:\/\/securityboulevard.com\/2026\/02\/ndss-2025-siguard-guarding-secure-inference-with-post-data-privacy\/ Publish Date: 2026-02-16&#8230;<\/p>\n","protected":false},"author":1,"featured_media":214198,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/securityboulevard.com\/wp-content\/uploads\/2018\/01\/TwitterLogo-002.jpg","fifu_image_alt":"","footnotes":""},"categories":[16],"tags":[],"class_list":["post-214197","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-privacy"],"_links":{"self":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/214197"}],"collection":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/comments?post=214197"}],"version-history":[{"count":1,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/214197\/revisions"}],"predecessor-version":[{"id":214199,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/214197\/revisions\/214199"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/214198"}],"wp:attachment":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=214197"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=214197"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=214197"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}