Deep learning models are vulnerable, but adversarial examples are even more vulnerable
Understanding intrinsic differences between adversarial examples and clean samples is key to enhancing DNN robustness and detection against adversarial attacks. This study first empirically finds that image-based adversarial examples are notably sensitive to occlusion. Controlled experiments on CIFAR-10 used nine canonical attacks (e.g., FGSM, PGD) to generate adversarial examples, paired with original samples for evaluation. We introduce Sliding Mask Confidence Entropy (SMCE) to quantify model confidence fluctuation under occlusion. Using 1800+ test images, SMCE calculations supported by Mask Entropy Field Maps and statistical distributions show adversarial examples have significantly higher confidence volatility under occlusion than originals. Based on this, we propose Sliding Window Mask-based Adversarial Example Detection (SWM-AED), which avoids catastrophic overfitting of conventional adversarial training. Evaluations across classifiers and attacks on CIFAR-10 demonstrate robust performance, with accuracy over 62% in most cases and up to 96.5%.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Adversarial Attack for Asynchronous Event-based Data
Deep neural networks (DNNs) are vulnerable to adversarial examples that are carefully designed to cause the deep learning model to make mistakes. Adversarial examples of 2D images and 3D point clouds have been extensivel…
Adversarial AttackAutonomous DrivingLEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions
Recent work shows that well-designed adversarial examples can fool deep neural networks (DNNs). Due to their transferability, adversarial examples can also attack target models without extra information, called black…
Adversarial AttackAdversarial examples in the physical world
Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machin…
BIG-bench Machine LearningVulnerability of Deep Reinforcement Learning to Policy Induction Attacks
Deep learning classifiers are known to be inherently vulnerable to manipulation by intentionally perturbed inputs, named adversarial examples. In this work, we establish that reinforcement learning techniques based on De…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Are Accuracy and Robustness Correlated?
Machine learning models are vulnerable to adversarial examples formed by applying small carefully chosen perturbations to inputs that cause unexpected classification errors. In this paper, we perform experiments on vario…
BIG-bench Machine LearningGeneral ClassificationObject Recognition