Fei Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Fei Wu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Jinbin Zhu
College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China
1 shared publication Jingjing Zhang
The Seventh Research Division, Beijing Institute of tracking and telecommunications technology, Beijing, China
1 shared publicationLimin Xiao
State Key Laboratory of Software Development Environment, Beihang University, Beijing, China
1 shared publication- Limin Xiao
Beihang University
1 shared publication Tong Guo
State Key Laboratory of Software Development Environment, Beihang University, Beijing, China
1 shared publication- Wenxue Yang
School of Computer Science and Engineering, Beihang University, Beijing 100191, China
1 shared publication
Latest Publications
- 28 February 2022
- Published by Springer Nature in Machine Vision and Applications
- Vol. 33 (2) , 1-16
Mitigating adversarial perturbations via weakly supervised object location and regions recombination
- 28 February 2022
- Published by Springer Nature in Machine Vision and Applications
- Vol. 33 (2) , 1-16
Mitigating adversarial perturbations via weakly supervised object location and regions recombination
- Open Access
- 3 October 2020
- Published by MDPI AG in Electronics
- Vol. 9 (10) , 1634
Adaptive Wiener Filter and Natural Noise to Eliminate Adversarial Perturbation
Deep neural network has been widely used in pattern recognition and speech processing, but its vulnerability to adversarial attacks also proverbially demonstrated. These attacks perform unstructured pixel-wise perturbation to fool the classifier, which does not affect the human visual system. The role of adversarial examples in the information security field has received increased attention across a number of disciplines in recent years. An alternative approach is “like cures like”. In this paper, we propose to utilize common noise and adaptive wiener filtering to mitigate the perturbation. Our method includes two operations: noise addition, which adds natural noise to input adversarial examples, and adaptive wiener filtering, which denoising the images in the previous step. Based on the study of the distribution of attacks, adding natural noise has an impact on adversarial examples to a certain extent and then they can be removed through adaptive wiener filter, which is an optimal estimator for the local variance of the image. The proposed improved adaptive wiener filter can automatically select the optimal window size between the given multiple alternative windows based on the features of different images. Based on lots of experiments, the result demonstrates that the proposed method is capable of defending against adversarial attacks, such as FGSM (Fast Gradient Sign Method), C&W, Deepfool, and JSMA (Jacobian-based Saliency Map Attack). By compared experiments, our method outperforms or is comparable to state-of-the-art methods.
- 3 October 2020
- Published by MDPI AG in Electronics
- Vol. 9 (10) , 1634
Open AccessAdaptive Wiener Filter and Natural Noise to Eliminate Adversarial Perturbation
Deep neural network has been widely used in pattern recognition and speech processing, but its vulnerability to adversarial attacks also proverbially demonstrated. These attacks perform unstructured pixel-wise perturbation to fool the classifier, which does not affect the human visual system. The role of adversarial examples in the information security field has received increased attention across a number of disciplines in recent years. An alternative approach is “like cures like”. In this paper, we propose to utilize common noise and adaptive wiener filtering to mitigate the perturbation. Our method includes two operations: noise addition, which adds natural noise to input adversarial examples, and adaptive wiener filtering, which denoising the images in the previous step. Based on the study of the distribution of attacks, adding natural noise has an impact on adversarial examples to a certain extent and then they can be removed through adaptive wiener filter, which is an optimal estimator for the local variance of the image. The proposed improved adaptive wiener filter can automatically select the optimal window size between the given multiple alternative windows based on the features of different images. Based on lots of experiments, the result demonstrates that the proposed method is capable of defending against adversarial attacks, such as FGSM (Fast Gradient Sign Method), C&W, Deepfool, and JSMA (Jacobian-based Saliency Map Attack). By compared experiments, our method outperforms or is comparable to state-of-the-art methods.