ETV-Attack: Efficient text-driven visual-variable adversarial attacks on visual question answering with pre-trained language models | OpenReview

ETV-Attack: Efficient text-driven visual-variable adversarial attacks on visual question answering with pre-trained language models

Open Webpage

Quanxing Xu, Ling Zhou, Xian Zhong, Feifei Zhang, Jinyu Tian, Xiaohan Yu, Rubing Huang

Published: 01 Aug 2026, Last Modified: 15 May 2026Pattern RecognitionEveryoneRevisionsCC BY-SA 4.0

External IDs:doi:10.1016/j.patcog.2026.113202

Loading