Poster · Sydney
Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios
- When
- Tue 8 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 1
- Authors
- Linus Folkerts, Will Payne, Simon Inman, Philippos M Giavridis, Joe Skinner, Sam Deverett, James Aung, Ekin Zorer, Michael Schmatz, Mahmoud Ghanem, John Wilkinson, Alan Steer and 3 more
- Organisations
- UK AI Security Institute, UK Department for Science, OpenAI, Imperial College London
- QRS classification
- Agentic AI, Language models, Safety, fairness and privacy