fcano@infosec.pubEnglish · 3 months agoAI Risk Repositoryplus-squareairisk.mit.eduexternal-linkmessage-square0fedilinkarrow-up16arrow-down11
arrow-up15arrow-down1external-linkAI Risk Repositoryplus-squareairisk.mit.edufcano@infosec.pubEnglish · 3 months agomessage-square0fedilink
fcano@infosec.pubEnglish · 3 months agoPractical LLM Security: Takeaways From a Year in the Trenches - Black Hat USA 2024 | Briefings Schedulewww.blackhat.comexternal-linkmessage-square0fedilinkarrow-up15arrow-down11
arrow-up14arrow-down1external-linkPractical LLM Security: Takeaways From a Year in the Trenches - Black Hat USA 2024 | Briefings Schedulewww.blackhat.comfcano@infosec.pubEnglish · 3 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 5 months agoStealing everything you’ve ever typed or viewed on your own Windows PC is now possible with two lines of code — inside the Copilot+ Recall disaster.doublepulsar.comexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkStealing everything you’ve ever typed or viewed on your own Windows PC is now possible with two lines of code — inside the Copilot+ Recall disaster.doublepulsar.comylai@lemmy.mlEnglish · 5 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 7 months agoAnyscale addresses critical vulnerability on Ray framework — but thousands were still exposedventurebeat.comexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkAnyscale addresses critical vulnerability on Ray framework — but thousands were still exposedventurebeat.comylai@lemmy.mlEnglish · 7 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 8 months agoAI hallucinates software packages and devs download them – even if potentially poisoned with malwarewww.theregister.comexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkAI hallucinates software packages and devs download them – even if potentially poisoned with malwarewww.theregister.comylai@lemmy.mlEnglish · 8 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 8 months agoWhy Are Large AI Models Being Red Teamed?spectrum.ieee.orgexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkWhy Are Large AI Models Being Red Teamed?spectrum.ieee.orgylai@lemmy.mlEnglish · 8 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 10 months agoHow 'sleeper agent' AI assistants can sabotage codewww.theregister.comexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkHow 'sleeper agent' AI assistants can sabotage codewww.theregister.comylai@lemmy.mlEnglish · 10 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 10 months agoNIST: If someone's trying to sell you some secure AI, it's snake oilwww.theregister.comexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkNIST: If someone's trying to sell you some secure AI, it's snake oilwww.theregister.comylai@lemmy.mlEnglish · 10 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 11 months agoBoffins devise 'universal backdoor' for image models to cause AI hallucinationswww.theregister.comexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkBoffins devise 'universal backdoor' for image models to cause AI hallucinationswww.theregister.comylai@lemmy.mlEnglish · 11 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 1 year agoLLM Finetuning Risksllm-tuning-safety.github.ioexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkLLM Finetuning Risksllm-tuning-safety.github.ioylai@lemmy.mlEnglish · 1 year agomessage-square0fedilink
ylai@lemmy.mlEnglish · 1 year agoAre Local LLMs Useful in Incident Response? - SANS Internet Storm Centerisc.sans.eduexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkAre Local LLMs Useful in Incident Response? - SANS Internet Storm Centerisc.sans.eduylai@lemmy.mlEnglish · 1 year agomessage-square0fedilink
ylai@lemmy.mlEnglish · 1 year agoMicrosoft Bing Chat spotted pushing malware via bad adswww.theregister.comexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkMicrosoft Bing Chat spotted pushing malware via bad adswww.theregister.comylai@lemmy.mlEnglish · 1 year agomessage-square0fedilink
ylai@lemmy.mlEnglish · 1 year agoNew AI Beats DeepMind’s AlphaGo Variants 97% Of The Time!plus-squarewww.youtube.comexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkNew AI Beats DeepMind’s AlphaGo Variants 97% Of The Time!plus-squarewww.youtube.comylai@lemmy.mlEnglish · 1 year agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 1 year agoIdentifying AI-generated images with SynthIDwww.deepmind.comexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkIdentifying AI-generated images with SynthIDwww.deepmind.comCapt. AIn@infosec.pubMEnglish · 1 year agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 1 year agoThinking about the security of AI systemswww.ncsc.gov.ukexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkThinking about the security of AI systemswww.ncsc.gov.ukCapt. AIn@infosec.pubMEnglish · 1 year agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 1 year agoGitHub - google/model-transparencyplus-squaregithub.comexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkGitHub - google/model-transparencyplus-squaregithub.comCapt. AIn@infosec.pubMEnglish · 1 year agomessage-square0fedilink
kristoff@infosec.pubEnglish · 1 year agodisinformation videos on AI ?plus-squaremessage-squaremessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squaredisinformation videos on AI ?plus-squarekristoff@infosec.pubEnglish · 1 year agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 1 year agoUniversal and Transferable Attacks on Aligned Language Modelsllm-attacks.orgexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkUniversal and Transferable Attacks on Aligned Language Modelsllm-attacks.orgCapt. AIn@infosec.pubMEnglish · 1 year agomessage-square0fedilink
netrom@infosec.pubEnglish · 1 year agoOWASP Top 10 for LLMs (v1.0)plus-squareowasp.orgexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkOWASP Top 10 for LLMs (v1.0)plus-squareowasp.orgnetrom@infosec.pubEnglish · 1 year agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 1 year agoCybercriminals train AI chatbots for phishing, malware attacksplus-squarewww.bleepingcomputer.comexternal-linkmessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkCybercriminals train AI chatbots for phishing, malware attacksplus-squarewww.bleepingcomputer.comCapt. AIn@infosec.pubMEnglish · 1 year agomessage-square0fedilink