Poster Sat, Sep 12, 2026 • 1:30 AM – 3:30 AM PDT ExHall # 367

Prefill-Time Interventions against Adversarial Attacks on Large Vision-Language Models

Zhewen Yao ⋅ Yao Zhu ⋅ Shiliang Zhang

Keywords: Federated, Continual & Efficient Learning; Model Security