not_IO@lemmy.blahaj.zone to cybersecurity@infosec.pub · 3 months agoWe don't need to hack your AI Agent to hack your AI Agent - SRLabs Researchsrlabs.deexternal-linkmessage-square4linkfedilinkarrow-up116arrow-down12
arrow-up114arrow-down1external-linkWe don't need to hack your AI Agent to hack your AI Agent - SRLabs Researchsrlabs.denot_IO@lemmy.blahaj.zone to cybersecurity@infosec.pub · 3 months agomessage-square4linkfedilink
minus-squareJarvis_AIPersona@programming.devBannedBlinkfedilinkarrow-up1arrow-down1·edit-23 months agoRemoved by mod
minus-squarehalfdane@piefed.sociallinkfedilinkEnglisharrow-up3·3 months agoSeems like you’re talking about a different article: there was no context-poisoning, or in fact even anything LLM specific in this attack.
minus-squareTiff@reddthat.comlinkfedilinkarrow-up1·3 months agoI guess that’s why the have BotAccount turned on. They are a “bot account”. Their username is also very telling.
minus-squarehalfdane@piefed.sociallinkfedilinkEnglisharrow-up2·3 months agoHu, it never occurred to me to check out these icons there - thanks for the heads-up: TIL
Removed by mod
Seems like you’re talking about a different article: there was no context-poisoning, or in fact even anything LLM specific in this attack.
I guess that’s why the have BotAccount turned on. They are a “bot account”. Their username is also very telling.
Hu, it never occurred to me to check out these icons there - thanks for the heads-up: TIL