artifex@piefed.social to Technology@beehaw.orgEnglish · 2 months agoAnthropic says its own AI models breached three companies during security teststechcrunch.comexternal-linkmessage-square13linkfedilinkarrow-up151arrow-down16file-textcross-posted to: technology@lemmy.world
arrow-up145arrow-down1external-linkAnthropic says its own AI models breached three companies during security teststechcrunch.comartifex@piefed.social to Technology@beehaw.orgEnglish · 2 months agomessage-square13linkfedilinkfile-textcross-posted to: technology@lemmy.world
minus-squarestoy@lemmy.ziplinkfedilinkEnglisharrow-up4·2 months agoWhat I think happened is that, they had their AI model analyze the source code, have it work to find vulnerabilities, and then used those to attack systems
What I think happened is that, they had their AI model analyze the source code, have it work to find vulnerabilities, and then used those to attack systems