Poster · Sydney

The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play

Name: The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play
Start: 2026-12-09T10:00:00+11:00
End: 2026-12-09T13:00:00+11:00
Location: Hall 1-4, ICC Sydney

When: Wed 9 Dec 2026, 10:00–13:00 AEDT
Where: Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session: Sydney Poster Session 3
Oral: Oral of this paper
Authors: Gabriele La Malfa, Emanuele La Malfa, Saar Cohen, Jie Zhang, Michael Luck, Michael Wooldridge, Elizabeth Black
Organisations: King's College London, University of Oxford, IDAI, University of Sussex
QRS classification: Safety, fairness and privacy

Open in schedule Official page