#red-teaming

#red-teaming

Last month, at the 33rd annual DEF CON, the world's largest hacker convention in Las Vegas, Anthropic researcher Keane Lucas took the stage. A former U.S. Air Force captain with a Ph.D. in electrical and computer engineering from Carnegie Mellon, Lucas wasn't there to unveil flashy cybersecurity exploits. Instead, he showed how Claude, Anthropic's family of large language models, has quietly outperformed many human competitors in hacking contests - the kind used to train and test cybersecurity skills in a safe, legal environment.

Researchers identified 139 novel methods to cause AI systems to misbehave, including generating misinformation and leaking personal data, during a red teaming exercise.