Anthropic Red Team Blog

Research and insights from the Anthropic Red Team

RSS Feed

Subscribe with any RSS reader

Subscribe via RSS

JSON Feed

Subscribe with a JSON Feed reader

Subscribe via JSON

Latest Articles

Measuring LLMs’ impact on N-day exploits
June 8, 2026
Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
June 3, 2026
Measuring LLMs’ ability to develop exploits
May 22, 2026
Coordinated Vulnerability Disclosure Dashboard
May 22, 2026
Assessing Claude Mythos Preview’s cybersecurity capabilities
April 7, 2026
Reverse engineering Claude's CVE-2026-2796 exploit
March 6, 2026
Partnering with Mozilla to improve Firefox’s security
March 6, 2026
Evaluating and mitigating the growing risk of LLM-discovered 0-days
February 5, 2026
AI models are showing a greater ability to find and exploit vulnerabilities on realistic cyber ranges
January 16, 2026
Finding bugs across the Python ecosystem with Claude and property-based testing
January 14, 2026
Experimenting with AI to defend critical infrastructure
January 8, 2026
Project Vend: Phase two
December 18, 2025
AI agents find $4.6M in blockchain smart contract exploits
December 1, 2025
Project Fetch: Can Claude train a robot dog?
November 12, 2025
Building AI for cyber defenders
September 29, 2025
Why do we take LLMs seriously as a potential source of biorisk?
September 5, 2025
Developing nuclear safeguards for AI through public-private partnership
August 21, 2025
Claude is competitive with humans in (some) cyber competitions
August 9, 2025
Detailed cyber evaluations of Claude 4
July 15, 2025
Project Vend: Can Claude run a small shop? (And why does that matter?)
June 27, 2025
LLMs with cyber toolkits can conduct multistage cyber operations on business-sized computer networks
June 13, 2025