Anthropic's Mythos AI model identified unspecified vulnerabilities in classified U.S. government systems during a partnered testing exercise with intelligence agencies. The article does not provide technical details on the nature of the vulnerabilities, their attack vectors, CVSS scores, or specific affected systems. No patch or workaround information is disclosed, as the report focuses on the discovery event rather than the vulnerabilities' technical characteristics.
A U.S. official told The Associated Press on Tuesday that one of Anthropic’s artificial intelligence models had identified vulnerabilities in highly sensitive and secure U.S. government computer systems during a testing exercise. The official, who spoke on the condition of anonymity to discuss the matter, said Anthropic had teamed up with U.S. intelligence agencies to […] The post Anthropic’s Mythos Model Found Vulnerabilities in Classified US Government Systems, Official Says appeared first on SecurityWeek .