Poster · Sydney
SudoBench: A Contextual Authorization Benchmark for LLM Agents
- 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
- Vincent Siu, Tianneng Shi, Shangding Gu, Zhun Wang, Dawn Song, Chenguang Wang
- Organisations
- University of California, Santa Cruz, University of California, Berkeley, Shanghai Jiao Tong University
- QRS classification
- Agentic AI, Language models, Safety, fairness and privacy