Zhijin Ge

Zhijin Ge

Auto-generated profile, based on publicly available information

Zhijin Ge

Xidian University, Xi'an, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 October 2023
Verified
Conference Paper
Open access
ZGZhijin Ge
Zhijin Ge
Fanhua ShangFanhua Shang
Fanhua Shang
HLHongying Liu
Hongying Liu
YLYuanyuan Liu
Yuanyuan Liu
LWLiang Wan
Liang Wan
XWXiaosen Wang
Xiaosen Wang
Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high success rates in the white-box setting, they also exhibit weak transferability in the black-box setting. Recently, various methods have been proposed to improve adversarial transferability, in which the input transformation is one of the most effective methods. In this work, we notice that existing input transformation-based works mainly adopt the transformed data in the same domain for augmentation. Inspired by domain generalization, we aim to further improve the transferability using the data augmented from different domains. Specifically, a style transfer network can alter the distribution of low-level visual features in an image while preserving semantic content for humans. Hence, we propose a novel attack method named Style Transfer Method (STM) that utilizes a proposed arbitrary style transfer network to transform the images into different domains. To avoid inconsistent semantic information of stylized images for the classification network, we fine-tune the style transfer network and mix up the generated images added by random noise with the original images to maintain semantic consistency and boost input diversity. Extensive experimental results on the ImageNet-compatible dataset show that our proposed method can significantly improve the adversarial transferability on either normally trained models or adversarially trained models than state-of-the-art input transformation-based attacks. Code is available at: https://github.com/Zhijin-Ge/STM.

11 October 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
HLHongying Liu
Hongying Liu
ZGZhijin Ge
Zhijin Ge
ZZzhenyu zhou
zhenyu zhou
Fanhua ShangFanhua Shang
Fanhua Shang
YLYuanyuan Liu
Yuanyuan Liu
LJLicheng Jiao
Licheng Jiao
Deep neural networks (DNNs) play key roles in various artificial intelligence applications such as image classification and object recognition. However, a growing number of studies have shown that there exist adversarial examples in DNNs, which are almost imperceptibly different from the original samples but can greatly change the output of DNNs. Recently, many white-box attack algorithms have been proposed, and most of the algorithms concentrate on how to make the best use of gradients per iteration to improve adversarial performance. In this article, we focus on the properties of the widely used activation function, rectified linear unit (ReLU), and find that there exist two phenomena (i.e., wrong blocking and over transmission) misguiding the calculation of gradients for ReLU during backpropagation. Both issues enlarge the difference between the predicted changes of the loss function from gradients and corresponding actual changes and misguide the optimized direction, which results in larger perturbations. Therefore, we propose a universal gradient correction adversarial example generation method, called ADV-ReLU, to enhance the performance of gradient-based white-box attack algorithms such as fast gradient signed method (FGSM), iterative FGSM (I-FGSM), momentum I-FGSM (MI-FGSM), and variance tuning MI-FGSM (VMI-FGSM). Through backpropagation, our approach calculates the gradient of the loss function with respect to the network input, maps the values to scores, and selects a part of them to update the misguided gradients. Comprehensive experimental results on ImageNet and CIFAR10 demonstrate that our ADV-ReLU can be easily integrated into many state-of-the-art gradient-based white-box attack algorithms, as well as transferred to black-box attacks, to further decrease perturbations measured in the ${\ell _2}$ -norm.

25 February 2026 in Journal of Computational and Applied Mathematics
Verified
Journal Article
Closed access
GYGonglin Yuan
Gonglin Yuan
YZYingjie Zhou
Yingjie Zhou
Fanhua ShangFanhua Shang
Fanhua Shang
ZGZhijin Ge
Zhijin Ge
ZJZhongzhou Jin
Zhongzhou Jin