logo
today local_bar
Transferable Adversarial Attacks

1 paper across 1 session

Poster Session 5

1 paper
Friday, December 5, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
#1513 · Xiaojun Jia, Sensen Gao, Simeng Qin, Tianyu Pang, Chao Du, Yihao Huang, Xinfeng Li, Yiming Li, Bo Li, Yang Liu

FOA-Attack enhances targeted adversarial transferability to closed-source MLLMs by optimally aligning global and local features.