Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain

No. 11: AAAI-21 Technical Tracks 11

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 35

AAAI Technical Track on Machine Learning IV

Deep neural networks (DNNs) have been shown to be vulnerable against adversarial examples (AEs), which are maliciously designed to cause dramatic model output errors. In this work, we reveal that normal examples (NEs) are insensitive to the fluctuations occurring at the highly-curved region of the decision boundary, while AEs typically designed over one single domain (mostly spatial domain) exhibit exorbitant sensitivity on such fluctuations. This phenomenon motivates us to design another classifier (called dual classifier) with transformed decision boundary, which can be collaboratively used with the original classifier (called primal classifier) to detect AEs, by virtue of the sensitivity inconsistency. When comparing with the state-of-the-art algorithms based on Local Intrinsic Dimensionality (LID), Mahalanobis Distance (MD), and Feature Squeezing (FS), our proposed Sensitivity Inconsistency Detector (SID) achieves improved AE  detection performance and superior generalization capabilities, especially in the challenging cases where the adversarial perturbation levels are small. Intensive experimental results on ResNet and VGG validate the superiority of the proposed SID.  

10.1609/aaai.v35i11.17187