Irregular Details How a Naming Error Let AI Models Attack a Real Company
The AI security testing firm has shared information on a recently disclosed incident involving Anthropic AI models. The post Irregular Details How a Naming Error Let AI Models Attack a Real Company appeared first on SecurityWeek.
AI safety testing firm Irregular has published its account of an incident in which models being evaluated inside one of its testing environments took offensive security actions against real systems rather than the simulated targets they were meant to attack.
The Israeli company, which last year raised $80 million in funding, has been in the news in recent weeks after it came to light that AI models it tested on behalf of OpenAI, Anthropic, and Meta escaped their test environments and carried out real-world attacks.
Irregular’s core business involves partnering with major AI labs to stress-test models before they are released to the public, running controlled simulations designed to measure a model’s capabilities in vulnerability research and offensive cyber tasks.
Related breach coverage
- Comp AI Raises $34 Million for AI-Native Compliance and Security2026-09-17
The company plans to expand into continuous cybersecurity, offering security testing across applications and infrastructure. The post Comp AI Raises $34 Million for AI-Native Compliance and Security appeared first on SecurityWeek.
- Personal, Financial Info Exposed in Revolut Data Breach2026-09-14
The company unintentionally disclosed users’ information to a third party impersonating a government agency. The post Personal, Financial Info Exposed in Revolut Data Breach appeared first on SecurityWeek.
- Widened Scan Turns Up Fourth Rogue Claude Cyber Incident2026-09-10
Anthropic is most concerned about Claude Mythos 5’s reckless behavior after recent incidents in which real systems were hacked. The post Widened Scan Turns Up Fourth Rogue Claude Cyber Incident appeared first on SecurityWeek.
- Anthropic Details Response to Security Incidents, Unveils Enterprise Safeguards2026-09-02
Anthropic introduced Enterprise Frontier Safeguards (EFS), a system that combines zero data retention with automated monitoring for misuse. The post Anthropic Details Response to Security Incidents, Unveils Enterprise Safeguards appeared first on SecurityWeek.