Wikimedia Foundation found “rogue” OpenAI agents on its wikis, raising concerns about risks to its free knowledge projects and the open web.

CrowdStrike Intelligence identified infrastructure associated with a targeted campaign against South Korean financial institutions that resulted in exfiltrated data.

OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents in which their frontier models took steps that outside evaluators would consider problematic, sources told Axios.

The incident is the first known breach to affect a government agency, and Australia's prime minister has vowed to hold OpenAI accountable.

The U.S. Justice Department said an Iranian security ministry operates the fake activist persona known as Handala, which claimed responsibility for the destructive hack targeting medical tech giant Stryker.

The European Union on Monday imposed sanctions against ​two China-based and one Iranian company ‌for cyberattacks against EU member states.
The EU listed China-based Integrity Technology Group and Anxun Information ​Technology, and Iranian company Emennet Pasargad.

Hannah Neumann was targeted in a cyber-espionage operation by an infamous Iranian hacking group earlier this year, she said.