Chinese hackers used our AI to attack world's top firms: Anthropic
Anthropic said that a Chinese hacking group exploited its Claude AI systems in September to launch a cyberattack on the world's major firms. To bypass safety rules, the hackers broke down malicious tasks into small, harmless-looking requests and tricked its Agentic model into thinking it was performing defensive cybersecurity testing. They initially attacked 30 targets, including financial firms.