Anthropic opens its most powerful AI models to more security teams

Anthropic is expanding a program that allows vetted ⁠cyber security professionals ⁠to test its most powerful AI models with fewer safeguards, after its Project Glasswing initiative helped uncover more than 100,000 software vulnerabilities this year.

Its partners under Glasswing, an ‌initiative aimed at securing the world’s most critical ‌software, ‌found at least 129,000 verified vulnerabilities ‌between April and July. Anthropic’s own open-source ⁠scanning found 5500 more between April and October.

More than 33,000 have so far been rated critical or high severity.

Anthropic said the figures are likely an undercount and expects the ​true impact to be at least five times higher, as the data comes from a survey of a ⁠limited number of partners.

The revamped Cyber Verification Program, or CVP, combines two programs Anthropic has run for the past six months.

The first, Glasswing, gave organisations securing critical software access to Claude Mythos, Anthropic’s most cyber-capable family of models.

The second, the original CVP, gave vetted security teams reduced safeguards on Claude Opus and Sonnet models.

The company’s April ​unveiling of Claude Mythos Preview raised ⁠fears that AI could hack software before it ⁠had been secured. 

The new program has three tiers, each with its own verification ​requirements and security controls. All three include access to Claude Opus ‌5.5, Sonnet ⁠5.5, Mythos 5.1 and future models.

The Defence tier covers work such as incident response and malware analysis. Security teams, critical infrastructure operators, open-source maintainers and ‌researchers with a record of reported vulnerabilities can apply.

The Red Team tier adds authorised penetration testing and red teaming, but only organisations can apply.

The Specialised tier has the fewest restrictions and ​is reserved for a small group of organisations authorized to test safety-critical systems such as power grids, flight systems and interbank transfer infrastructure. 

Anthropic vets each member ‌together with ⁠the US government, and existing ​Glasswing members will move into this tier.

About Author

AndyC

Andy Curtis is an award-winning security consultant, researcher and public speaker. He has been working in the computer security industry since the early 1990s, having been employed by state and federal government, leading healthcare and banking providers across three continents. He has given talks about computer security for some of the world’s largest companies, worked with law enforcement agencies on investigations into hacking groups, and is a regular voice on TV and radio explaining IT security threats.

See author's posts