Poster · Sydney
Beyond the Prompt: Leveraging Pre-Decoding States for Jailbreak Detection in dLLMs
- 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
- Adam Hazimeh, Amel Abdelraheem, Ke Wang, Mariam Salman, Ljiljana Dolamic, Gérôme Bovet, Pascal Frossard
- Organisations
- EPFL, American University of Beirut, Armasuisse
- QRS classification
- Safety, fairness and privacy