About the Team

As AI systems become more advanced, the potential for misuse of their cyber capabilities may pose a threat to the security of organisations and individuals. Cyber capabilities also form common bottlenecks in scenarios across other AI risk areas such as harmful outcomes from biological and chemical capabilities and from autonomous systems. One approach to better understanding these risks is by conducting robust empirical tests of AI systems so we can better understand how capable they currently are when it comes to performing cyber security tasks.

The AI Security Institute’s Cyber Evaluations Team is developing first-of-its-kind government-run infrastructure to benchmark the progress of advanced AI capabilities in the domain of cyber security. Our goal is to carry out and publish scientific research supporting a global effort to understand the risks and improve the safety of advanced AI systems. Our current focus is on doing this by buil...