Anthropic Threat Report Details Disrupted AI Misuse, Including Yemen Missile Guidance Effort
Anthropic published a threat intelligence report detailing how it disrupted efforts to misuse its Claude AI models for cyberattacks, surveillance, influence operations, and other threats. The report includes cases where scientists used the models for research that could have helped develop biological weapons, and a Yemen-based cell using Claude to develop missile guidance software, with some but not all requests blocked.
Coverage timeline
Hacker Newsjbegley
Techmeme
Anthropic : Anthropic publishes a threat intelligence report on how it disrupted efforts to misuse Claude for cyberattacks, influence operations, surveillance, and more — Cyber operations Surveillance operations Influence operations Conventional weapons Biological misuse Scams and fraud Illicit distillation
Dustin Volz / New York Times : Anthropic says it disrupted several potential plots this year by scientists using its models for research that could have helped develop biological weapons — In a new report, the A.I. start-up added that it could not determine if the research was legitimate or nefarious, leading the company to shut down the work.
Bloomberg : Threat intelligence report: Anthropic says it disrupted a Yemen-based guided weapons engineering cell using Claude to develop guidance software for missiles — Anthropic PBC uncovered a group in northern Yemen — where Iran-backed Houthi militants operate — using its Claude AI model …
The Verge AIHayden Field
After admitting earlier this year that its AI models had hacked other companies' systems on a handful of occasions, Anthropic released a new report on Wednesday detailing the attacks. It reveals a string of incidents displaying what Anthropic deems its models' single-minded "recklessness" - and will likely fuel already raging concerns about cybersecurity and AI. In Anthropic's report, it detailed four cases this year in which its own AI models hacked an external company or exploited vulnerabilities. In one, an "internal, general-purpose research model" broke into third-party systems, using access tokens and passwords and downloading files. … Read the full story at The Verge.
Hacker NewsAlien1Being
# Rebels used Anthropic’s AI bot to develop guided weapons, report says Militants in Yemen sought to use a coding tool to produce guided rockets and missiles, the firm found, noting it was able to block some but not all the requests. September 11, 2026 at 11:24 a.m. EDT Yesterday at 11:24 a.m. EDT 50 Make us preferred on Google Houthi rebels in Sanaa, Yemen, on Thursday. (AP) By Pranshu Verma Militants in Yemen used an artificial-intelligence tool to try to develop location-guidance software for weapons, according to a threat report released by Anthropic, an incident that comes amid rising public concern that advanced AI could be harmful to human life. Get concise answers to your questions. Try Ask The Post AI. The 7 logo The 7 LIVE Previous Next Hannah Sampson September 11, 2026 Will full water bottles finally be allowed through airport security? Cleve R. Wootson Jr. September 11, 2026 For years, Bush was mocked for this 9/11 moment. Now he’s painted it. Evan Halper September 11, 2026
Related stories
Anthropic expands Cyber Verification Program with three tiers, reports 5,500+ verified model vulnerabilities
Anthropic launched an expanded three-tier version of its Cyber Verification Program (CVP), integrating Project Glasswing and granting vetted cybersecurity professionals access to its latest models. The company reported 5,500+ verified vulnerabilities in its models from April to October, with Glasswing partners finding 129,000+ more between April and July, of which 33,000+ were critical or high severity.
2 reports · 1 sources
METR: AI outputs should be treated as untrusted input to prevent cover-ups
METR published an analysis arguing that AI systems could conceal misbehavior from human reviewers, citing recent incidents where AI pursued unauthorized goals but left evidence in logs and reasoning traces. The report recommends treating AI outputs as untrusted input and treating recording and display systems as security-critical infrastructure, given expected advances in AI situational awareness and cyber capabilities.
1 reports · 1 sources
DOD stops using Anthropic tools; Claude used in Iran ops last week
The US Department of Defence has stopped using Anthropic's AI tools, according to an official. Sources say Claude was in use as recently as last week, including in military operations against Iran.
US FTC Expands Probe of OpenAI, Anthropic, Plans Formal Information Demands
The US Federal Trade Commission is expanding its probe of Anthropic, OpenAI, and other frontier AI labs, according to sources cited by the New York Post. The agency plans to issue formal demands for information as part of the sweeping investigation into product risks.
2 reports · 2 sources210 points · 160 comments
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe