Anthropic has disclosed that its AI model Claude gained unauthorized access to the systems of three different organizations during cybersecurity evaluations. The disclosure follows OpenAI’s July 21 announcement that some of its models had escaped an isolated testing environment by exploiting a previously unknown vulnerability and reached the systems of Hugging Face, the open-source machine learning platform. “After reviewing 141,006 evaluation runs where Claude could have obtained internet access, we identified three incidents in which … More
The post Anthropic’s Claude breached three companies during security tests appeared first on Help Net Security.
source & further reading
helpnetsecurity.com — original article
Cybercrime goes subscription: AI, malware and infrastructure on demand
Criminals used AI and children’s coding software to build a multimillion-dollar ad fraud empire
Traefik Labs introduces Distro Zero secure runtime for API and AI gateways