Hacking on AI
Advanced AI Red Teaming Tools
Perform adversarial research and execute operations in Strikes. Categorize, assess, and mitigate enumerated risks presented by AI deployments.
Attack models in deployed settings
Launch the latest attacks against deployed AI systems
Extend Spyglass by adding targets, datasets, and scoring
Integrate your research and workflows with the SDK
Perform analysis and create reports to share findings
attack ai
Attack and optimize AI systems
Use Spyglass Runs to identify security risks and vulnerabilities in your AI applications during development and after deployment in an operational setting.
Perform research and Execute assessments
Test SYSTEMS in A Deployed Setting
Generate actionable insights about vulnerabilities
Compare performance across multiple models
Download results for Training and analysis