Zhengyu Shang

Mr. Zhengyu Shang

orcid

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
6 November 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AIAhmed Dawod Mohammed Ibrahum
Ahmed Dawod Mohammed Ibrahum
ZSZhengyu Shang
Zhengyu Shang
JHJang-Eui Hong
Jang-Eui Hong
Kolmogorov–Arnold Networks (KANs) are a novel class of neural network architectures based on the Kolmogorov–Arnold representation theorem, which has demonstrated potential advantages in accuracy and interpretability over Multilayer Perceptron (MLP) models. This paper comprehensively evaluates the robustness of various KAN architectures—including KAN, KAN-Mixer, KANConv_KAN, and KANConv_MLP—against adversarial attacks, which constitute a critical aspect that has been underexplored in current research. We compare these models with MLP-based architectures such as MLP, MLP-Mixer, and ConvNet_MLP across three traffic sign classification datasets: GTSRB, BTSD, and CTSD. The models were subjected to various adversarial attacks (FGSM, PGD, CW, and BIM) with varying perturbation levels and were trained under different strategies, including standard training, adversarial training, and Randomized Smoothing. Our experimental results demonstrate that KAN-based models, particularly the KAN-Mixer, exhibit superior robustness to adversarial attacks compared to their MLP counterparts. Specifically, the KAN-Mixer consistently achieved lower Success Attack Rates (SARs) and Degrees of Change (DoCs) across most attack types and datasets while maintaining high accuracy on clean data. For instance, under FGSM attacks with ϵ=0.01, the KAN-Mixer outperformed the MLP-Mixer by maintaining higher accuracy and lower SARs. Adversarial training and Randomized Smoothing further enhanced the robustness of KAN-based models, with t-SNE visualizations revealing more stable latent space representations under adversarial perturbations. These findings underscore the potential of KAN architectures to improve neural network security and reliability in adversarial settings.

3 February 2025 in Expert Systems with Applications
Verified
Journal Article
Open access
MHManzoor Hussain
Manzoor Hussain
ZSZhengyu Shang
Zhengyu Shang
JHJang-Eui Hong
Jang-Eui Hong

28 August 2025 in IEEE Access
Verified
Journal Article
Open access
MHManzoor Hussain
Manzoor Hussain
ZSZhengyu Shang
Zhengyu Shang
AIAhmed Dawod Mohammed Ibrahum
Ahmed Dawod Mohammed Ibrahum
JHJang-Eui Hong
Jang-Eui Hong
Adversarial training is a widely used method to improve the robustness of deep learning models in various applications. Although adversarial training enhances the robustness of the target model, it also suffers from an accuracy versus robustness trade-off, meaning that while improving robustness, the accuracy of the target model decreases. Moreover, they also suffer from catastrophic overfitting, where these methods offer reasonable robustness against specific adversarial attacks, but they become ineffective against others. Thus, to solve these issues, we proposed Prediction Error-Guided Adversarial Training (PEGAT). In this method, we first evaluate the normally trained target models against adversarial samples and then calculate class-wise prediction error in terms of loss in the F1-score, which we refer to as PEGAT scores. In the second phase, use the PEGAT scores as guidance to assign weights during the adversarial training process. In this phase, PEGAT adaptively assigns higher weights to classes with high PEGAT scores and lower weights to classes with low PEGAT scores. The PEGAT guides the models to focus on those classes where they struggle to maintain a higher F1 score in the first phase. By doing so, not only is the adversarial robustness of the target model increased, but also the issues such as the accuracy versus robustness tradeoff, catastrophic overfitting, and generalizability are addressed. Evaluating the PEGAT on classification models used in intelligent autonomous vehicle perception systems, we found that the technique could improve the robustness of WideResNet18, WideResNet34, and WideResNet50 by 16%, 6%, and 5%, respectively, without suffering from the aforementioned issues.

17 June 2023
Verified
Conference Paper
Open access
ZDZiqi Dong
Ziqi Dong
YLYan Long
Yan Long
ZSZhengyu Shang
Zhengyu Shang
CDCong Ding
Cong Ding
DWDing Wei
Ding Wei
Aiming at the problem that both security and efficiency cannot be achieved in the process of transmitting smart meter terminal data to the power control center, this paper proposes a secure smart meter data transmission method based on regional space aggregation. First of all, by analyzing the characteristics of smart meter data transmission business, starting from the three dimensions of data transmission privacy, accuracy, and security, a coupled and interconnected spatial element index system is constructed; then, a smart meter area space aggregation algorithm for data security transmission is designed, and the data security aggregation transmission is realized based on the homomorphism of the secret sharing scheme; Finally, by comparing the method proposed in this paper with the dominant algorithms in recent years, the validity and practicability of the proposed method are verified.