[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-ai-explainability-tools-can-leak-training-data-here-is-a-fix":10,"sections":34},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},3776,"ai-explainability-tools-can-leak-training-data-here-is-a-fix","AI Explainability Tools Can Leak Training Data - Here is a Fix","Researchers propose a training-time defense that closes a privacy gap opened by the very tools designed to make AI more transparent.","AI explanation interfaces, built to make models trustworthy, turn out to be a useful attack surface for stealing information about training data.\n\nA new paper introduces TIER, short for Trajectory-Invariant Explanation Regularization, a defense built into the model training process itself. The attack it counters works by feeding carefully chosen inputs to an AI model and watching how its confidence score drops across a sequence of steps - a pattern that leaks whether a specific data point was in the training set. Existing defenses largely target simpler membership-inference methods and miss this trajectory-based variant entirely. TIER fights back by penalizing erratic confidence-drop patterns during training and using a statistical technique called KL-divergence to keep the distribution of those drops similar between training members and non-members.\n\nThe stakes here are higher than they look. Membership-inference attacks are a known compliance risk under privacy regulations, and the irony is that explanation APIs - the features companies add to satisfy transparency demands - are the lever being pulled. A defense that works at training time rather than patching the API layer is a meaningful architectural shift.\n\nThe researchers report that TIER preserves both model accuracy and explanation quality, though independent replication on production-scale models would be the real test of that claim.","[\"ai\",\"privacy\",\"security\",\"machine-learning\"]","2026-07-07T04:00:00.000Z","2026-07-07T08:15:11.520Z","2026-07-07T08:15:14.389Z","published",null,[],"ai",[24,26,27,28],"privacy","security","machine-learning",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.02903",0,{"sections":35},[36,40,44,49,54,59,64,69,74,78,83,87,92,97],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":41,"slug":27,"count":42,"latest_published_at":43},"Security",294,"2026-07-15T19:59:48.000Z",{"name":45,"slug":46,"count":47,"latest_published_at":48},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":58},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":63},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":65,"slug":66,"count":67,"latest_published_at":68},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":70,"slug":71,"count":72,"latest_published_at":73},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":75,"slug":76,"count":77,"latest_published_at":18},"Dev Tools","dev-tools",59,{"name":79,"slug":80,"count":81,"latest_published_at":82},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":84,"slug":85,"count":81,"latest_published_at":86},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":93,"slug":94,"count":95,"latest_published_at":96},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":98,"slug":99,"count":100,"latest_published_at":101},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]