Litcius/Paper detail

Detection of adversarial attacks based on differences in image entropy

Gwonsang Ryu, Daeseon Choi

2023International Journal of Information Security16 citationsDOIOpen Access PDF

Abstract

Abstract Although deep neural networks (DNNs) have achieved high performance across various applications, they are often deceived by adversarial examples generated by adding small perturbations. To combat adversarial attacks, many detection methods have been proposed, including feature squeezing and trapdoor. However, these methods rely on the output of DNNs or involve training a separate network to detect adversarial examples, which leads to high computational costs and low efficiency. In this study, we propose a simple and effective approach called the entropy-based detector (EBD) to protect DNNs from various adversarial attacks. EBD detects adversarial examples by comparing the difference in entropy between the input sample before and after bit depth reduction. We show that EBD can detect over 98% of the adversarial examples generated by attacks using fast-gradient sign method, basic iterative method, momentum iterative method, DeepFool and CW attacks when the false positive rate is 2.5% for CIFAR-10 and ImageNet datasets.

Topics & Concepts

Adversarial systemComputer scienceDeep neural networksDetectorArtificial intelligenceEntropy (arrow of time)Artificial neural networkPattern recognition (psychology)Machine learningAlgorithmTelecommunicationsQuantum mechanicsPhysicsAdversarial Robustness in Machine LearningIntegrated Circuits and Semiconductor Failure AnalysisAnomaly Detection Techniques and Applications