How we contain Claude across products
…This article shares what’s held up, what’s broken, and what we’ve learned about agent security along the way. Three types of risk, three components of defense Security risks to…
Search
The Long-Term Benefit Trust
…Basic Structure and Features The Anthropic Long-Term Benefit Trust (LTBT, or Trust) is an independent body comprising five Trustees with backgrounds and expertise in AI safety, national security, public policy, and…
Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
…These findings point to a landscape where the dividing line between low and high-risk actors is no longer technical skill but orchestration, and where defenses, detections, and the shared frameworks we…
Focus areas for The Anthropic Institute
…signal for significant change and disruption. Research on the societal areas most in need of investment in resilience in the face of new AI-enabled security risks. More detailed information about how…
LLMs and biorisk
…We believe it’s important to support transparency norms—like the push for developers to have a Secure Development Framework (like Anthropic’s Responsible Scaling Policy ) and publish results of model evaluations…
Building AI for cyber defenders
…our Hai security agents by 44% while improving accuracy by 25%, helping us reduce risk for businesses with confidence.” According to Sven Krasser, Senior Vice President for Data Science and Chief Scientist…
Redeploying Claude Fable 5
…Our engagement spanned the Office of the National Cyber Director, the Office of Science and Technology Policy, the Department of the Treasury, the Department of Commerce (including CAISI), and relevant national security…
Measuring LLMs’ ability to develop exploits
…If you’re interested in helping us with our efforts, we have job openings available for research scientists and engineers , threat investigators , policy managers , offensive security researchers , security engineers , and many others…
Claude Fable 5 and Claude Mythos 5
…Our wider suite of safeguards is discussed and evaluated in the model’s system card and our most recent risk report . Safety classifiers The frontier cybersecurity and research biology capabilities of Mythos…
Claude for Financial Services
…Box enables secure document management and data room analysis Daloopa supplies high-quality fundamentals and KPIs from all public filings, disclosures and presentations Databricks offers unified analytics for big data and AI…