haxor@derp.fooMB to Hacker News@derp.fooEnglish · 1 year agoUniversal and Transferable Adversarial Attacks on Aligned Language Modelsllm-attacks.orgexternal-linkmessage-square0fedilinkarrow-up13arrow-down11file-textcross-posted to: ai_infosec@infosec.pubaistuff@lemdro.idtechnews@radiation.party
arrow-up12arrow-down1external-linkUniversal and Transferable Adversarial Attacks on Aligned Language Modelsllm-attacks.orghaxor@derp.fooMB to Hacker News@derp.fooEnglish · 1 year agomessage-square0fedilinkfile-textcross-posted to: ai_infosec@infosec.pubaistuff@lemdro.idtechnews@radiation.party