AI RESEARCH

A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models

arXiv CS.CV

ArXi:2603.26984v1 Announce Type: new Despite the rapid progress in multimodal models and Large Visual-Language Models (LVLM), they remain highly susceptible to adversarial perturbations, raising serious concerns about their reliability in real-world use. While adversarial