Weixiong Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Weixiong Hu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Chuanjing Zhang
Cyberspace Institute of Advanced Technology, Guangzhou University, 47875 Guangzhou, Guangdong China
2 shared publications - Le Wang
Guangzhou University
2 shared publications - Zhaoquan Gu
Harbin Institute of Technology
2 shared publications - Chunsheng Zhu
Shenzhen Technology University
1 shared publication - Hui Lu
Guangzhou University
1 shared publication - Lihua Yin
Guangzhou University
1 shared publication
Latest Publications
- 22 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 8 (2) , 921-932
Gradient Shielding: Towards Understanding Vulnerability of Deep Neural Networks
Deep neural networks (DNNs) have been widely adopted but they are vulnerable to intentionally crafted adversarial examples. Various attack methods against DNNs have been proposed, yet there still lacks theoretical explanation of adversarial examples. In this paper, we aim to understand adversarial examples from the attacking process and we assume adding perturbations to the key/sensitive regions of the image could fool image classification DNNs. We propose gradient shielding to verify the assumption which ignores insensitive information during generating adversarial examples. Specifically, we propose interactive gradient shielding (IGS) method which selects sensitive regions and then applies gradient-based attack. To remove region selection, we propose adaptive gradient shielding (AGS) method which ignores insensitive gradients automatically. We conduct extensive experiments to evaluate the performance and the results also corroborate our perspective. With this method, we won the first place in IJCAI-AAAC 2019 Non-targeted Adversarial Attack competition.
- 22 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 8 (2) , 921-932
Gradient Shielding: Towards Understanding Vulnerability of Deep Neural Networks
Deep neural networks (DNNs) have been widely adopted but they are vulnerable to intentionally crafted adversarial examples. Various attack methods against DNNs have been proposed, yet there still lacks theoretical explanation of adversarial examples. In this paper, we aim to understand adversarial examples from the attacking process and we assume adding perturbations to the key/sensitive regions of the image could fool image classification DNNs. We propose gradient shielding to verify the assumption which ignores insensitive information during generating adversarial examples. Specifically, we propose interactive gradient shielding (IGS) method which selects sensitive regions and then applies gradient-based attack. To remove region selection, we propose adaptive gradient shielding (AGS) method which ignores insensitive gradients automatically. We conduct extensive experiments to evaluate the performance and the results also corroborate our perspective. With this method, we won the first place in IJCAI-AAAC 2019 Non-targeted Adversarial Attack competition.
- Open Access
- 3 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 25262-25271
Restricted Region Based Iterative Gradient Method for Non-Targeted Attack
Neural networks have been widely applied but they are still vulnerable to adversarial examples. More and more defense models have been proposed and they can resist the attacks to the neural networks. In order to generate adversarial examples with good transferability, we propose the restricted region based iterative gradient method (RRI-GM) for non-targeted attack, which aims at generating adversarial examples to make black-box defense models output wrong decision. We first use object detection algorithm to restrict some key regions in the images, since we regard perturbation in the key region affects more than the whole image. To improve the efficiency of attacks, we use gradient-based attack methods and they show good performance. In addition, the process is iterated for multiple rounds to generate adversarial examples with good transferability. Furthermore, we conduct extensive experiments to validate the effectiveness of the proposed method, and the results show that our method can achieve good attack performance against black-box defense models.
- 3 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 25262-25271
Open AccessRestricted Region Based Iterative Gradient Method for Non-Targeted Attack
Neural networks have been widely applied but they are still vulnerable to adversarial examples. More and more defense models have been proposed and they can resist the attacks to the neural networks. In order to generate adversarial examples with good transferability, we propose the restricted region based iterative gradient method (RRI-GM) for non-targeted attack, which aims at generating adversarial examples to make black-box defense models output wrong decision. We first use object detection algorithm to restrict some key regions in the images, since we regard perturbation in the key region affects more than the whole image. To improve the efficiency of attacks, we use gradient-based attack methods and they show good performance. In addition, the process is iterated for multiple rounds to generate adversarial examples with good transferability. Furthermore, we conduct extensive experiments to validate the effectiveness of the proposed method, and the results show that our method can achieve good attack performance against black-box defense models.