Paper Info
Title
Maximum Mean Discrepancy Test Is Aware Of Adversarial Attacks
Abstract
The maximum mean discrepancy (MMD) test could in principle detect any distributional discrepancy between two datasets. However, it has been shown that the MMD test is unaware of adversarial attacks-the MMD test failed to detect the discrepancy between natural and adversarial data. Given this phenomenon, we raise a question: are natural and adversarial data really from different distributions? The answer is affirmative-the previous use of the MMD test on the purpose missed three key factors, and accordingly, we propose three components. Firstly, Gaussian kernel has limited representation power, and we replace it with an effective deep kernel. Secondly, test power of the MMD test was neglected, and we maximize it following asymptotic statistics. Finally, adversarial data may be non-independent, and we overcome this issue with the wild bootstrap. By taking care of the three factors, we verify that the MMD test is aware of adversarial attacks, which lights up a novel road for adversarial data detection based on two-sample tests.
Year
Venue
DocType
2021
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139
Conference
Volume
ISSN
Citations 
139
2640-3498
0
PageRank 
References 
Authors
0.34
0
7
Name
Order
Citations
PageRank
Ruize Gao100.34
Feng Liu2808.59
Jingfeng Zhang301.35
Bo Han46123.20
Tongliang Liu5127.58
Gang Niu620436.78
Masashi Sugiyama73353264.24