ylai@lemmy.mlEnglish · 2 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.plus-squaredoublepulsar.comexternal-linkmessage-square0fedilinkarrow-up144arrow-down10
arrow-up144arrow-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.plus-squaredoublepulsar.comylai@lemmy.mlEnglish · 2 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 4 months agoAnyscale addresses critical vulnerability on Ray framework — but thousands were still exposedplus-squareventurebeat.comexternal-linkmessage-square0fedilinkarrow-up14arrow-down11
arrow-up13arrow-down1external-linkAnyscale addresses critical vulnerability on Ray framework — but thousands were still exposedplus-squareventurebeat.comylai@lemmy.mlEnglish · 4 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 4 months agoAI hallucinates software packages and devs download them – even if potentially poisoned with malwareplus-squarewww.theregister.comexternal-linkmessage-square3fedilinkarrow-up142arrow-down10
arrow-up142arrow-down1external-linkAI hallucinates software packages and devs download them – even if potentially poisoned with malwareplus-squarewww.theregister.comylai@lemmy.mlEnglish · 4 months agomessage-square3fedilink
ylai@lemmy.mlEnglish · 4 months agoWhy Are Large AI Models Being Red Teamed?plus-squarespectrum.ieee.orgexternal-linkmessage-square1fedilinkarrow-up17arrow-down14
arrow-up13arrow-down1external-linkWhy Are Large AI Models Being Red Teamed?plus-squarespectrum.ieee.orgylai@lemmy.mlEnglish · 4 months agomessage-square1fedilink
ylai@lemmy.mlEnglish · 6 months agoHow 'sleeper agent' AI assistants can sabotage codeplus-squarewww.theregister.comexternal-linkmessage-square0fedilinkarrow-up16arrow-down10
arrow-up16arrow-down1external-linkHow 'sleeper agent' AI assistants can sabotage codeplus-squarewww.theregister.comylai@lemmy.mlEnglish · 6 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 7 months agoNIST: If someone's trying to sell you some secure AI, it's snake oilplus-squarewww.theregister.comexternal-linkmessage-square1fedilinkarrow-up133arrow-down10
arrow-up133arrow-down1external-linkNIST: If someone's trying to sell you some secure AI, it's snake oilplus-squarewww.theregister.comylai@lemmy.mlEnglish · 7 months agomessage-square1fedilink
ylai@lemmy.mlEnglish · 8 months agoBoffins devise 'universal backdoor' for image models to cause AI hallucinationsplus-squarewww.theregister.comexternal-linkmessage-square0fedilinkarrow-up13arrow-down10
arrow-up13arrow-down1external-linkBoffins devise 'universal backdoor' for image models to cause AI hallucinationsplus-squarewww.theregister.comylai@lemmy.mlEnglish · 8 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 10 months agoLLM Finetuning Risksplus-squarellm-tuning-safety.github.ioexternal-linkmessage-square0fedilinkarrow-up13arrow-down11
arrow-up12arrow-down1external-linkLLM Finetuning Risksplus-squarellm-tuning-safety.github.ioylai@lemmy.mlEnglish · 10 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 10 months agoAre Local LLMs Useful in Incident Response? - SANS Internet Storm Centerplus-squareisc.sans.eduexternal-linkmessage-square0fedilinkarrow-up14arrow-down10
arrow-up14arrow-down1external-linkAre Local LLMs Useful in Incident Response? - SANS Internet Storm Centerplus-squareisc.sans.eduylai@lemmy.mlEnglish · 10 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 10 months agoMicrosoft Bing Chat spotted pushing malware via bad adsplus-squarewww.theregister.comexternal-linkmessage-square0fedilinkarrow-up125arrow-down10
arrow-up125arrow-down1external-linkMicrosoft Bing Chat spotted pushing malware via bad adsplus-squarewww.theregister.comylai@lemmy.mlEnglish · 10 months agomessage-square0fedilink
ylai@lemmy.mlEnglish · 10 months agoNew AI Beats DeepMind’s AlphaGo Variants 97% Of The Time!plus-squarewww.youtube.comexternal-linkmessage-square0fedilinkarrow-up111arrow-down15
arrow-up16arrow-down1external-linkNew AI Beats DeepMind’s AlphaGo Variants 97% Of The Time!plus-squarewww.youtube.comylai@lemmy.mlEnglish · 10 months agomessage-square0fedilink
Capt. AInMEnglish · 11 months agoIdentifying AI-generated images with SynthIDplus-squarewww.deepmind.comexternal-linkmessage-square0fedilinkarrow-up14arrow-down10
arrow-up14arrow-down1external-linkIdentifying AI-generated images with SynthIDplus-squarewww.deepmind.comCapt. AInMEnglish · 11 months agomessage-square0fedilink
Capt. AInMEnglish · 11 months agoThinking about the security of AI systemsplus-squarewww.ncsc.gov.ukexternal-linkmessage-square0fedilinkarrow-up16arrow-down10
arrow-up16arrow-down1external-linkThinking about the security of AI systemsplus-squarewww.ncsc.gov.ukCapt. AInMEnglish · 11 months agomessage-square0fedilink
Capt. AInMEnglish · 11 months agoGitHub - google/model-transparencyplus-squaregithub.comexternal-linkmessage-square0fedilinkarrow-up16arrow-down10
arrow-up16arrow-down1external-linkGitHub - google/model-transparencyplus-squaregithub.comCapt. AInMEnglish · 11 months agomessage-square0fedilink
kristoffEnglish · 11 months agodisinformation videos on AI ?plus-squaremessage-squaremessage-square10fedilinkarrow-up13arrow-down11
arrow-up12arrow-down1message-squaredisinformation videos on AI ?plus-squarekristoffEnglish · 11 months agomessage-square10fedilink
Capt. AInMEnglish · 11 months agoUniversal and Transferable Attacks on Aligned Language Modelsplus-squarellm-attacks.orgexternal-linkmessage-square0fedilinkarrow-up18arrow-down10
arrow-up18arrow-down1external-linkUniversal and Transferable Attacks on Aligned Language Modelsplus-squarellm-attacks.orgCapt. AInMEnglish · 11 months agomessage-square0fedilink
netromEnglish · 1 year agoOWASP Top 10 for LLMs (v1.0)plus-squareowasp.orgexternal-linkmessage-square1fedilinkarrow-up113arrow-down10
arrow-up113arrow-down1external-linkOWASP Top 10 for LLMs (v1.0)plus-squareowasp.orgnetromEnglish · 1 year agomessage-square1fedilink
Capt. AInMEnglish · 1 year agoCybercriminals train AI chatbots for phishing, malware attacksplus-squarewww.bleepingcomputer.comexternal-linkmessage-square0fedilinkarrow-up18arrow-down11
arrow-up17arrow-down1external-linkCybercriminals train AI chatbots for phishing, malware attacksplus-squarewww.bleepingcomputer.comCapt. AInMEnglish · 1 year agomessage-square0fedilink
stevedidwhat_infosecEnglish · 1 year agoGPT Malware Creationplus-squaremessage-squaremessage-square5fedilinkarrow-up15arrow-down111
arrow-up1-6arrow-down1message-squareGPT Malware Creationplus-squarestevedidwhat_infosecEnglish · 1 year agomessage-square5fedilink
Capt. AInMEnglish · 1 year agoAdversarial suffixes that circumvent the alignment of open source LLMS, ChatGPT, Claude, Bard, and LLaMA-2twitter.comexternal-linkmessage-square0fedilinkarrow-up18arrow-down11
arrow-up17arrow-down1external-linkAdversarial suffixes that circumvent the alignment of open source LLMS, ChatGPT, Claude, Bard, and LLaMA-2twitter.comCapt. AInMEnglish · 1 year agomessage-square0fedilink
