haxor@derp.fooMB to Hacker News@derp.fooEnglish · 1 year agoUniversal and Transferable Adversarial Attacks on Aligned Language Modelsllm-attacks.orgexternal-linkmessage-square0fedilinkarrow-up12arrow-down10file-textcross-posted to: ai_infosec@infosec.pubaistuff@lemdro.idmachinelearning@kbin.social
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.idmachinelearning@kbin.social