Pudutr0n@lemmy.world to Showerthoughts@lemmy.world · 3 days agoSomeone should make a community to freely distribute examples of data poisoning people can randomly put in their social media posts/images to sabotage AImessage-squaremessage-square29fedilinkarrow-up1120arrow-down14
arrow-up1116arrow-down1message-squareSomeone should make a community to freely distribute examples of data poisoning people can randomly put in their social media posts/images to sabotage AIPudutr0n@lemmy.world to Showerthoughts@lemmy.world · 3 days agomessage-square29fedilink
minus-squarechaogomu@lemmy.worldlinkfedilinkEnglisharrow-up7·3 days agoThere’s a new technique that uses the AIs “thinking” tags to get it to do things that are otherwise banned by policy. I’ll have to find the article again. But due to the way LLMs work, they can’t defend against this sort of attack.
minus-squarechaogomu@lemmy.worldlinkfedilinkEnglisharrow-up3·3 days agoAnd here’s some explanations of how various attacks work. https://github.com/nukIeer/AI-Prompt-Injection-Cheatsheet https://dev.to/praneet_gogoi_beastsoul/how-hackers-trick-ai-the-hidden-world-of-prompt-injections-and-jailbreaks-4nge https://developer.nvidia.com/blog/how-hackers-exploit-ais-problem-solving-instincts/
There’s a new technique that uses the AIs “thinking” tags to get it to do things that are otherwise banned by policy.
I’ll have to find the article again. But due to the way LLMs work, they can’t defend against this sort of attack.
And here’s some explanations of how various attacks work.
https://github.com/nukIeer/AI-Prompt-Injection-Cheatsheet
https://dev.to/praneet_gogoi_beastsoul/how-hackers-trick-ai-the-hidden-world-of-prompt-injections-and-jailbreaks-4nge
https://developer.nvidia.com/blog/how-hackers-exploit-ais-problem-solving-instincts/