期刊论文

Liu, H

英文

Pattern Recognition

0031-3203

2024

147

110127

10.1016/j.patcog.2023.110127

National Natural Science Foundation of China [62172181]

本校为第一且通讯机构

Although deep neural networks (DNNs) have performed well on many perceptual tasks, they are vulnerable to adversarial examples that are generated by adding slight but maliciously crafted perturbations to benign images. Adversarial detection is an important technique for identifying adversarial examples before they are entered into target DNNs. Previous studies that were performed to detect adversarial examples either targeted specific attacks or required expensive computation. Designing a lightweight unsupervised detector is still a challenging problem. In this paper, we propose an AutoEncoder...