"I'm allowed to do this": how attackers talk past AI safeguards
by Ellsworth Toohey from Boing Boing on (#77G4G)
Getting an AI model to launch a cyberattackusually just takes asking the right way. Cisco Talos researchers say that claiming you own the servers you are attacking often works, and so does calling the job a capture-the-flag contest or a bug bounty. - Read the rest
The post "I'm allowed to do this": how attackers talk past AI safeguards appeared first on Boing Boing.