Poster · Sydney
Latent-space Attacks for Refusal Evasion in Language Models
- When
- Thu 10 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 5
- Authors
- Giorgio Piras, Raffaele Mura, Fabio Brau, Maura Pintor, Luca Oneto, Fabio Roli, Battista Biggio
- Organisations
- University of Cagliari, University of Genoa
- QRS classification
- Language models, Safety, fairness and privacy