…exploited by attackers. Our own Coordinated Vulnerability Disclosure policy takes this approach. However, this means that disclosed vulnerabilities are a lagging indicator of the accelerating frontier of AI models’ cyber capabilities: we…
…Public and private sector cyber operators and security professionals use advanced AI systems to reduce the attack surface in America and other democracies and blunt the CCP’s ability to gain and…
Frontier Red Team Detailed cyber evaluations of Claude 4 Jul 15, 2025 Anthropic (with Pattern Labs ) We believe we are at a crucial period for cybersecurity and AI, with models advancing toward…
…One particularly important safety mechanism involves classifiers —smaller automated AI systems that, during an interaction, detect when the model is asked to perform a potentially harmful cybersecurity task (or produces potentially harmful…
…What's next for AI-enabled cybersecurity These early signs of AI-enabled exploit development underscore the importance of accelerating the find-and-fix process for defenders. Towards that end, we want…
…Introduction AI cyber capabilities are accelerating rapidly: they are now capable of tasks from orchestrating complex network intrusions to augmenting state-level espionage . Benchmarks, like CyberGym and Cybench , are valuable for tracking…
…cybersecurity team also built a set of specialized Claude review agents that run throughout the development process. A “red team” agent probes an application from the outside, the way an attacker might…
…My secondary concern is the risk that powerful AI models may be misused to carry out cyberattacks or biological attacks, and may have serious alignment problems . Open-weights models—it does not…
…Further in the future, we hope AI will play a crucial role in designing the next generation of stronger and more resilient cryptographic schemes. An improved attack on reduced-round AES In…
…Footnotes Related content Introducing the Services Track and Partner Hub of the Claude Partner Network What we learned mapping a year’s worth of AI-enabled cyber threats As AI transforms the…