[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-method-certifies-llm-safety-across-multi-turn-chats":10,"sections":35},{"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":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},5810,"new-method-certifies-llm-safety-across-multi-turn-chats","New Method Certifies LLM Safety Across Multi Turn Chats","Researchers built a math framework that proves how long a chatbot stays safe under multi-turn jailbreak attempts, replacing rough guesses with actual bounds.","A new certification framework promises to tell you, with math instead of vibes, how many conversation turns it takes before a chatbot's safety guarantees start to crumble.\n\nResearchers describe Multi-Turn Certified Robustness (MTCR), a framework that models chatbot safety across a conversation as a State-Adversarial MDP, essentially treating each turn as a move in a game against an attacker trying to manipulate context over time. Prior certified-robustness work only handled single-turn inputs, and simply chaining those single-turn guarantees together produces bounds that collapse exponentially the longer a conversation runs. MTCR instead uses compositional certification through embedding-space decomposition to get tighter lower bounds, plus a mechanism the paper calls safety persistence that slows the degradation rate from an exponential drop to a gentler one, while also producing matching upper bounds to show the estimates are as tight as they can be. The team tested it on six LLMs against both epsilon-bounded attacks and Crescendo-style attacks, a known technique that escalates a jailbreak gradually across turns.\n\nThis matters because most safety evaluation still happens one prompt at a time, even though real jailbreaks rarely work that way. Crescendo and similar multi-turn attacks succeed precisely by exploiting context that builds slowly, and a model that looks robust on turn one can still be walked into unsafe territory by turn ten. Having a certified, interpretable estimate of how many turns a model can withstand gives developers something closer to a warranty than a hope.\n\nIt is still a lab result, not a product: the paper reports that empirical safety beat the certified bounds in testing, which is reassuring but also a reminder that a certified floor is, by design, more conservative than reality.","[\"llm safety\",\"jailbreaks\",\"ai security\",\"certified robustness\"]","2026-08-24T04:00:00.000Z","2026-08-24T04:52:11.806Z","2026-08-24T04:52:23.721Z","published",null,[],"ai",[26,27,28,29],"llm safety","jailbreaks","ai security","certified robustness",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.20820",0,{"sections":36},[37,41,45,50,55,60,65,70,75,80,85,90,95,100],{"name":38,"slug":24,"count":39,"latest_published_at":40},"AI",3325,"2026-08-24T09:09:31.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":18},"Security","security",461,{"name":46,"slug":47,"count":48,"latest_published_at":49},"Policy","policy",218,"2026-08-23T19:30:00.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",145,"2026-08-22T21:25:33.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",95,"2026-08-18T16:05:00.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Science","science",91,"2026-08-20T10:01:48.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",73,"2026-08-18T07:51:50.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",69,"2026-08-18T04:00:00.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Startups","startups",50,"2026-08-22T16:23:09.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"General","general",33,"2026-08-18T22:18:13.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":101,"slug":102,"count":103,"latest_published_at":104},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]