How to Hack an AI (And Why YOU Should Care)
In order to improve security, “good” hackers tried to outsmart AI models. Because hacked AI could tell you how to build a bomb or steal your private data. How does this work and why is the problem hard to fix?
▸ subscribe to our channel: https://goo.gl/UupwgM
#AI #artificialintelligence #hack #hacker #redteam #defcon #jailbreak #chatgpt #openai #prompt #promptinjection #llm #largelanguagemodel #bing #microsoft