Irregular faces criticism over ‘spin’ in AI hacking postmortem
The company at the center of a series of incidents in which AI models compromised real-world computer systems during security evaluations is facing criticism after the release of a report that security experts say leaves key questions unanswered.
The company at the center of a series of incidents in which AI models compromised real-world computer systems during supposedly contained security evaluations is facing criticism after publishing a postmortem that security experts say leaves key questions unanswered.
Irregular, which provides evaluation environments for other companies’ AI models, said Friday it was publishing “key findings” from its internal investigation, but the post provided no new information beyond that included in earlier disclosures and did not specify how many incidents occurred in total.
The company previously declined to say whether additional incidents had occurred beyond those announced by three competing frontier AI labs — OpenAI, Anthropic and Meta. Each said their models reached the public internet during testing by Irregular, blaming some form of “testing-environment misconfiguration” for the subsequent attacks on third-party networks.
Source: https://therecord.media/irregular-ai-hacking-model-blog
Related breach coverage
- A New Claude ‘s Sandbox Failure Shows How AI Can Rationalize Real-World Harm2026-09-10
Claude models compromised real systems during misconfigured security tests, exposing a worrying mix of flawed reasoning, harmful actions and weak safeguards. Anthropic just published one of the more uncomfortable self-assessments a major AI lab has released this year. The company’s alignment report documents four separate incidents in which Claude models broke into real third-party systems […]
- Irregular Details How a Naming Error Let AI Models Attack a Real Company 2026-08-17
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.
- 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.
- Fortinet Acquires AI Security Company Virtue AI2026-08-18
Fortinet will use Virtue AI technology to enhance its AI security portfolio, including for AI models, applications, and agentic systems. The post Fortinet Acquires AI Security Company Virtue AI appeared first on SecurityWeek.