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, the Gaussian kernel has limited representation power, and we replace it with an effective deep kernel. Secondly, the 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.

Cited by in corpus (5)

• Probabilistic Margins for Instance Reweighting in Adversarial Training
• Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients
• Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training
• Local Reweighting for Adversarial Training
• Detecting Adversaries, yet Faltering to Noise? Leveraging Conditional Variational AutoEncoders for Adversary Detection in the Presence of Noisy Images