WHWeixiong Hu

Weixiong Hu

*This is an algorithmically generated author record based on publicly available information.

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:


Latest Publications

  • Gradient Shielding: Towards Understanding Vulnerability of Deep Neural Networks

    by Zhaoquan Gu, Weixiong Hu, Chuanjing Zhang, Hui Lu, Lihua Yin, Le Wang

    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

    Restricted Region Based Iterative Gradient Method for Non-Targeted Attack

    by Zhaoquan Gu, Weixiong Hu, Chuanjing Zhang, Le Wang, Chunsheng Zhu, Zhihong Tian

    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.