kerntucky@infosec.pubEnglish · 26 days agoMalicious ML models found on Hugging Face Hubplus-squarewww.helpnetsecurity.comexternal-linkmessage-square0fedilinkarrow-up18
arrow-up18external-linkMalicious ML models found on Hugging Face Hubplus-squarewww.helpnetsecurity.comkerntucky@infosec.pubEnglish · 26 days agomessage-square0fedilink
fcano@infosec.pubEnglish · 7 months agoAI Risk Repositoryplus-squareairisk.mit.eduexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkAI Risk Repositoryplus-squareairisk.mit.edufcano@infosec.pubEnglish · 7 months agomessage-square0fedilink
fcano@infosec.pubEnglish · 7 months agoPractical LLM Security: Takeaways From a Year in the Trenches - Black Hat USA 2024 | Briefings Scheduleplus-squarewww.blackhat.comexternal-linkmessage-square0fedilinkarrow-up12
arrow-up12external-linkPractical LLM Security: Takeaways From a Year in the Trenches - Black Hat USA 2024 | Briefings Scheduleplus-squarewww.blackhat.comfcano@infosec.pubEnglish · 7 months agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 2 years agoIdentifying AI-generated images with SynthIDplus-squarewww.deepmind.comexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkIdentifying AI-generated images with SynthIDplus-squarewww.deepmind.comCapt. AIn@infosec.pubMEnglish · 2 years agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 2 years agoThinking about the security of AI systemsplus-squarewww.ncsc.gov.ukexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkThinking about the security of AI systemsplus-squarewww.ncsc.gov.ukCapt. AIn@infosec.pubMEnglish · 2 years agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 2 years agoGitHub - google/model-transparencyplus-squaregithub.comexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkGitHub - google/model-transparencyplus-squaregithub.comCapt. AIn@infosec.pubMEnglish · 2 years agomessage-square0fedilink
kristoff@infosec.pubEnglish · 2 years agodisinformation videos on AI ?plus-squaremessage-squaremessage-square0fedilinkarrow-up11
arrow-up11message-squaredisinformation videos on AI ?plus-squarekristoff@infosec.pubEnglish · 2 years agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 2 years agoUniversal and Transferable Attacks on Aligned Language Modelsplus-squarellm-attacks.orgexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkUniversal and Transferable Attacks on Aligned Language Modelsplus-squarellm-attacks.orgCapt. AIn@infosec.pubMEnglish · 2 years agomessage-square0fedilink
netrom@infosec.pubEnglish · 2 years agoOWASP Top 10 for LLMs (v1.0)plus-squareowasp.orgexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkOWASP Top 10 for LLMs (v1.0)plus-squareowasp.orgnetrom@infosec.pubEnglish · 2 years agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 2 years agoCybercriminals train AI chatbots for phishing, malware attacksplus-squarewww.bleepingcomputer.comexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkCybercriminals train AI chatbots for phishing, malware attacksplus-squarewww.bleepingcomputer.comCapt. AIn@infosec.pubMEnglish · 2 years agomessage-square0fedilink
stevedidwhat_infosec@infosec.pubEnglish · 2 years agoGPT Malware Creationplus-squaremessage-squaremessage-square0fedilinkarrow-up11
arrow-up11message-squareGPT Malware Creationplus-squarestevedidwhat_infosec@infosec.pubEnglish · 2 years agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 2 years agoAdversarial suffixes that circumvent the alignment of open source LLMS, ChatGPT, Claude, Bard, and LLaMA-2plus-squaretwitter.comexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkAdversarial suffixes that circumvent the alignment of open source LLMS, ChatGPT, Claude, Bard, and LLaMA-2plus-squaretwitter.comCapt. AIn@infosec.pubMEnglish · 2 years agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 2 years ago(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMsplus-squaretwitter.comexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-link(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMsplus-squaretwitter.comCapt. AIn@infosec.pubMEnglish · 2 years agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 2 years agoIntro to ML Safety - Free courseplus-squarecourse.mlsafety.orgexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkIntro to ML Safety - Free courseplus-squarecourse.mlsafety.orgCapt. AIn@infosec.pubMEnglish · 2 years agomessage-square0fedilink
0xCBE@infosec.pubEnglish · 2 years agoA framework to securely use LLMs in companies - Part 1: Overview of Risksplus-squareboringappsec.substack.comexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkA framework to securely use LLMs in companies - Part 1: Overview of Risksplus-squareboringappsec.substack.com0xCBE@infosec.pubEnglish · 2 years agomessage-square0fedilink
Capt. AIn@infosec.pubMEnglish · 2 years agoArmy looking at the possibility of 'AI BOMs'plus-squaredefensescoop.comexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkArmy looking at the possibility of 'AI BOMs'plus-squaredefensescoop.comCapt. AIn@infosec.pubMEnglish · 2 years agomessage-square0fedilink
0xCBE@infosec.pubEnglish · 2 years agoImpact of remote-code execution vulnerability in LangChainplus-squarentietz.comexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkImpact of remote-code execution vulnerability in LangChainplus-squarentietz.com0xCBE@infosec.pubEnglish · 2 years agomessage-square0fedilink
0xCBE@infosec.pubEnglish · 2 years agoPoisonGPT: How we hid a lobotomized LLM on Hugging Face to spread fake newsplus-squareblog.mithrilsecurity.ioexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkPoisonGPT: How we hid a lobotomized LLM on Hugging Face to spread fake newsplus-squareblog.mithrilsecurity.io0xCBE@infosec.pubEnglish · 2 years agomessage-square0fedilink
Xavier Ashe@infosec.pubEnglish · 2 years agoGitHub - JetP1ane/Callisto: Callisto - An Intelligent Binary Vulnerability Analysis Toolplus-squaregithub.comexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkGitHub - JetP1ane/Callisto: Callisto - An Intelligent Binary Vulnerability Analysis Toolplus-squaregithub.comXavier Ashe@infosec.pubEnglish · 2 years agomessage-square0fedilink
Xavier Ashe@infosec.pubEnglish · 2 years agoGitHub - mahaloz/DAILA: A decompiler-unified plugin for accessing the OpenAI API to improve your decompilation experienceplus-squaregithub.comexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkGitHub - mahaloz/DAILA: A decompiler-unified plugin for accessing the OpenAI API to improve your decompilation experienceplus-squaregithub.comXavier Ashe@infosec.pubEnglish · 2 years agomessage-square0fedilink
