artifex@piefed.social to Technology@beehaw.orgEnglish · 27 days agoAnthropic says its own AI models breached three companies during security teststechcrunch.comexternal-linkmessage-square12fedilinkarrow-up16arrow-down10file-textcross-posted to: [email protected]
arrow-up16arrow-down1external-linkAnthropic says its own AI models breached three companies during security teststechcrunch.comartifex@piefed.social to Technology@beehaw.orgEnglish · 27 days agomessage-square12fedilinkfile-textcross-posted to: [email protected]
minus-squarestoy@lemmy.ziplinkfedilinkEnglisharrow-up2·27 days 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