[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-smarter-way-to-hide-your-private-data-from-ai-chatbots":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},3783,"a-smarter-way-to-hide-your-private-data-from-ai-chatbots","A Smarter Way to Hide Your Private Data from AI Chatbots","PromptPET picks the right obfuscation technique per prompt to keep your data private without making chatbot responses useless.","A new research system rewrites your chat prompts before they reach an AI chatbot — stripping sensitive details while keeping enough context to get a useful answer.\n\nResearchers introduced PromptPET, an LLM-based agent that applies one of four obfuscation techniques — redaction, abstraction, replacement, or a novel noising-and-denoising scheme — to sensitive parts of a user prompt. Rather than using a single blanket approach, PromptPET uses a reinforcement-learning-inspired rule optimizer to choose the best technique for each sensitive fragment. The system also draws on a data-type taxonomy to identify what counts as sensitive in the first place, and it explicitly scores the utility of the resulting chatbot response as part of its decision logic.\n\nThe stakes here are real: every time a user asks an AI chatbot for help, they risk leaking details that can be used to build a profile on them — sometimes without realizing it. PromptPET is notable because it attacks the problem client-side, meaning users don't have to trust the chatbot provider to handle their data carefully. On a real-world chat dataset, it matched the best privacy-utility tradeoff any single obfuscation method could achieve and outperformed prior approaches by a meaningful margin.\n\nThe hard part was always the tradeoff: anonymize too aggressively and the chatbot gives you a useless generic answer; anonymize too lightly and you've just handed over your data anyway. PromptPET doesn't eliminate that tension, but it automates navigating it — which is more than most privacy tools even attempt.","[\"ai\",\"privacy\",\"llm\",\"security\"]","2026-07-07T04:00:00.000Z","2026-07-07T08:26:28.258Z","2026-07-07T08:26:31.151Z","published",null,[],"ai",[24,26,27,28],"privacy","llm","security",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.02932",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":28,"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"]