Research
Research is where the products start
We work along the path from research to prototype to product, and try to keep that path visible.
Current directions
- Agentic AI SecuritySecurity properties of agentic systems
- Adversarial AI EvaluationEvaluation of model behaviour under adversarial input
- Privacy-Preserving AIPrivacy-preserving inference
- Model Monitoring & InterpretabilityMonitoring and interpretability for deployed models
Publications
Papers and reports
Nothing published yet
Papers, preprints and technical reports will appear here as they are released, each labelled with its actual status.
Let's build what comes next.
If you are working on something where intelligence and security both matter, we would like to hear about it.