Poster · Sydney
ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in 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
- Udari Madhushani Sehwag, Zhengyang Shan, Heming Liu, Dileepa Lakshan, Joseph Brandifino, Max Fenkell
- Organisations
- Scale AI, Boston University, University of Illinois Urbana-Champaign, ESOFT Uni
- QRS classification
- Agentic AI, Language models, Safety, fairness and privacy