Poster · Sydney

VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild

Name: VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild
Start: 2026-12-10T10:00:00+11:00
End: 2026-12-10T13:00:00+11:00
Location: Hall 1-4, ICC Sydney

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: Junlin Fang, Wenyu Chen, Reshmi Ghosh, Robert Sim, Ahmed Salem, Vitor Carvalho, Emily Lawton, Sharon Li, Jack Stokes, Sean Du
Organisations: Nanyang Technological University, Microsoft, University of Wisconsin-Madison
QRS classification: Language models, Computer vision

Open in schedule Official page