Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain

Abstract

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.

References in corpus (13)

• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Adversarially Robust Generalization Requires More Data
• The Space of Transferable Adversarial Examples
• Detecting Adversarial Samples from Artifacts
• On the (Statistical) Detection of Adversarial Examples
• On Detecting Adversarial Perturbations
• Understanding Measures of Uncertainty for Adversarial Example Detection
• Adversarial Training Can Hurt Generalization
• Curriculum Adversarial Training
• Detecting Adversarial Examples and Other Misclassifications in Neural Networks by Introspection
• A Geometric Perspective on the Transferability of Adversarial Directions

Cited by in corpus (3)

• What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction
• Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention
• Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent