Advancing methodologies for agentic evaluations across domains, including leakage of sensitive Information, fraud and cybersecurity threats.| AI Security Institute
The AI Security Institute is a directorate of the Department of Science, Innovation, and Technology that facilitates rigorous research to enable advanced AI governance.| AI Security Institute
We tested leading AI models for cyber, chemical, biological, and agent capabilities and safeguards effectiveness. Our first technical blog post shares a snapshot of our methods and results.| AI Security Institute