[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-researchers-use-psychology-tactics-to-jailbreak-chatbots":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},5841,"researchers-use-psychology-tactics-to-jailbreak-chatbots","Researchers Use Psychology Tactics to Jailbreak Chatbots","A new framework called PsychJail uses classic persuasion psychology across multi-turn conversations to break AI safety guardrails 87 percent of the time.","Turns out you can jailbreak an AI chatbot with a good argument, no hacking required.\n\nResearchers built PsychJail, a framework that turns established social-psychology persuasion tactics into a step-by-step attack plan for jailbreaking aligned language models. Instead of firing off one cleverly worded prompt, the system runs a multi-turn conversation, tracking how each message shifts the target's stance and choosing the next persuasion tactic based on the Persuasion Knowledge Model. A reinforcement-learning process rewards the attacker only when it shows well-formed reasoning at every turn, not just when it eventually gets through. Tested against four aligned models, PsychJail broke through safety guardrails 87.3% of the time on average, beating both single-turn and multi-turn jailbreak baselines on every model tried.\n\nThe more interesting result is not the headline success rate. It is that each model failed in a different, consistent way. The researchers identified four distinct fingerprints: models that cave to logical-sounding arguments, ones swayed by claimed credibility, ones vulnerable to a single repeated narrative, and ones broadly persuadable by almost any tactic. That is a more useful map for defenders than one aggregate score, since it implies different models need different psychological patches, not just better prompt filters.\n\nThe researchers call those four profiles a conjecture, not a finding, which is fair. Four models is a small sample for diagnosing personality types.","[\"jailbreaking\",\"llm safety\",\"red teaming\",\"ai security\"]","2026-08-25T04:00:00.000Z","2026-08-25T05:41:19.660Z","2026-08-25T05:41:31.594Z","published",null,[],"security",[26,27,28,29],"jailbreaking","llm safety","red teaming","ai security",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.23028",0,{"sections":36},[37,41,44,49,54,59,64,69,74,79,84,89,94,99],{"name":38,"slug":39,"count":40,"latest_published_at":18},"AI","ai",3329,{"name":42,"slug":24,"count":43,"latest_published_at":18},"Security",468,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",224,"2026-08-24T19:02:32.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":58},"Hardware","hardware",145,"2026-08-22T21:25:33.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":63},"Consumer Tech","consumer-tech",95,"2026-08-18T16:05:00.000Z",{"name":65,"slug":66,"count":67,"latest_published_at":68},"Science","science",91,"2026-08-20T10:01:48.000Z",{"name":70,"slug":71,"count":72,"latest_published_at":73},"Software","software",73,"2026-08-18T07:51:50.000Z",{"name":75,"slug":76,"count":77,"latest_published_at":78},"Dev Tools","dev-tools",69,"2026-08-18T04:00:00.000Z",{"name":80,"slug":81,"count":82,"latest_published_at":83},"Startups","startups",51,"2026-08-24T13:47:26.000Z",{"name":85,"slug":86,"count":87,"latest_published_at":88},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",33,"2026-08-18T22:18:13.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]