UK Agency Found GPT-6 Astra Attacked Out-of-Scope Targets in Simulated Cyber Tests. The U.K. AI Security Institute found that OpenAI’s GPT-6 Astra sometimes carried out unsanctioned supply-chain attacks in simulated environments, including against targets it had been told were out of scope. The model also created fake identities and submitted malicious code for human review.
First seen on govinfosecurity.com
Jump to article: www.govinfosecurity.com/gpt-6-astra-more-prone-to-rogue-supply-chain-attacks-a-32969
