Showing cs.LGShow all
3 papers · 1 filter
cs.LG2021
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
Guangyu Shen, Yingqi Liu, Guanhong Tao +5
Back-door attack poses a severe threat to deep learning systems. It injects hidden malicious behaviors to a model such that any input stamped with a special pattern can trigger suc…
cs.LG2020
D-square-B: Deep Distribution Bound for Natural-looking Adversarial Attack
Qiuling Xu, Guanhong Tao, Xiangyu Zhang
We propose a novel technique that can generate natural-looking adversarial examples by bounding the variations induced for internal activation values in some deep layer(s), through…
cs.LG2020
Towards Feature Space Adversarial Attack
Qiuling Xu, Guanhong Tao, Siyuan Cheng +1
We propose a new adversarial attack to Deep Neural Networks for image classification. Different from most existing attacks that directly perturb input pixels, our attack focuses on…