AdvDrop: Adversarial Attack to DNNs by Dropping Information

Autor:	Duan, Ranjie, Chen, Yuefeng, Niu, Dantong, Yang, Yun, Qin, A. K., He, Yuan
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Cryptography and Security Computer Science - Machine Learning Electrical Engineering and Systems Science - Image and Video Processing
Druh dokumentu:	Working Paper
Popis:	Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e.g. cartoon. However, in terms of visual perception of Deep Neural Networks (DNNs), the ability for recognizing abstract objects (visual objects with lost information) is still a challenge. In this work, we investigate this issue from an adversarial viewpoint: will the performance of DNNs decrease even for the images only losing a little information? Towards this end, we propose a novel adversarial attack, named \textit{AdvDrop}, which crafts adversarial examples by dropping existing information of images. Previously, most adversarial attacks add extra disturbing information on clean images explicitly. Opposite to previous works, our proposed work explores the adversarial robustness of DNN models in a novel perspective by dropping imperceptible details to craft adversarial examples. We demonstrate the effectiveness of \textit{AdvDrop} by extensive experiments, and show that this new type of adversarial examples is more difficult to be defended by current defense systems. Comment: Accepted to ICCV 2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2108.09034 Zobrazit plný text záznamu View this record from Arxiv