一作ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety
Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models
Liangsheng Liu · Si Chen · Jiamin Wu · Weiwei Feng · Zhixin Cheng · Xiaotian Yin · Wenfei Yang · Tianzhu Zhang