Junlin Fang, Wenyu Chen, Reshmi Ghosh, Robert Sim, Ahmed Salem, Vitor Carvalho, Emily Lawton, Sharon Li 0001, Jack W. Stokes, Sean Du. VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild. Trans. Mach. Learn. Res., 2026, 2026. [doi]
Abstract is missing.