【CVPR 2022 对抗攻击】Cross-Modal Transferable Adversarial Attacks from Images to Videos 派大鑫 AI小学生8 人赞同了该文章 作者均来自复旦大学,论文链接:CVPR 2022 Open Access Repository 简介 最近的研究表明,在一个白盒模型上制作的对抗性示例可以用来攻击其他黑盒模型。这种跨模型可移植性使得执行黑盒攻击成为...
Cross-Modal Transferable Adversarial Attacks from Images to Videos Zhipeng Wei1,2, Jingjing Chen1,2,† Zuxuan Wu1,2, Yu-Gang Jiang1,2 1Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University 2Shanghai Collaborative Innova...
魏志鹏. Cross-Modal Transferable Adversarial Attacks from Images to Videos[OL]. 2022-08-03 00:00. 线上. https://www.koushare.com/video/details/30521 复制 MLA 魏志鹏. Cross-Modal Transferable Adversarial Attacks from Images to Videos. https://www.koushare.com/video/details/30521. 线上. 复...
To bridge this gap, we propose a label independent cross-modal transferable adversarial video attack with sparse strategy called SS-CMT, which efficiently generates sparse adversarial video examples with low perturbations and high transferability. Specifically, we propose a sparse strategy to select ...
To bridge this gap, we propose a label independent cross-modal transferable adversarial video attack with sparse strategy called SS-CMT, which efficiently generates sparse adversarial video examples with low perturbations and high transferability. Specifically, we propose a sparse strategy to select ...