ijeffMA to AI StuffEnglish · edit-22 years agoUniversal and Transferable Attacks on Aligned Language Models - Carnegie Mellon Universityllm-attacks.orgexternal-linkmessage-square2fedilinkarrow-up112arrow-down12file-textcross-posted to: ai_infosec@infosec.pubtechnews@radiation.party
arrow-up110arrow-down1external-linkUniversal and Transferable Attacks on Aligned Language Models - Carnegie Mellon Universityllm-attacks.orgijeffMA to AI StuffEnglish · edit-22 years agomessage-square2fedilinkfile-textcross-posted to: ai_infosec@infosec.pubtechnews@radiation.party
Coverage: A New Attack Impacts Major AI Chatbots—and No One Knows How to Stop It - Wired Researchers discover new vulnerability in large language models - TechXplore Keeping the Baby While Losing the Bathwater: AI’s Efficiencies and Concerns Collide - Pymnts
minus-squarefidodo@lemmy.worldlinkfedilinkEnglisharrow-up1·2 years agoCouldn’t you just do a simple input classifier step to detect if there’s nonsense strings in the user input and then not respond? You could even just use a simplistic algorithm to detect weird input strings.
minus-squareijeffOPMAlinkfedilinkEnglisharrow-up1·2 years agoBing has a separate layer that attempts to step in to filter things, but false positives end up being pretty disruptive.
Couldn’t you just do a simple input classifier step to detect if there’s nonsense strings in the user input and then not respond? You could even just use a simplistic algorithm to detect weird input strings.
Bing has a separate layer that attempts to step in to filter things, but false positives end up being pretty disruptive.