2026
VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models
ICML 2026poster
Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimodal red-teaming methods largely rely on brittle templates, focus on single-attack settings, and expose only a narrow subse…