Poster Thu, Sep 10, 2026 • 1:30 AM – 3:30 AM PDT ExHall # 364

Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating

Xiangkui Cao ⋅ Jie Zhang ⋅ Meina Kan ⋅ Shiguang Shan ⋅ Xilin CHEN

Keywords: Vision-Language Models & Foundation Models