Guangxu Xie

Mr. Guangxu Xie

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
26 March 2024 in Electronics
Verified
Journal Article
Open access
PDF file
GXGuangxu Xie
Guangxu Xie
GHGaopan Hou
Gaopan Hou
Qingqi PeiQingqi Pei
Qingqi Pei
Haibo HuangHaibo Huang
Haibo Huang
Adversarial sample-based privacy protection has its own advantages compared to traditional privacy protections. Previous adversarial sample privacy protections have mostly been centralized or have not considered the issue of hardware device limitations when conducting privacy protection, especially on the user’s local device. This work attempts to reduce the requirements of adversarial sample privacy protections on devices, making the privacy protection more locally friendly. Adversarial sample-based privacy protections rely on deep learning models, which generally have a large number of parameters, posing challenges for deployment. Fortunately, the model structural pruning technique has been proposed, which can be employed to reduce the parameter count of deep learning models. Based on the model pruning technique Depgraph and existing adversarial sample privacy protections AttriGuard and MemGuard, we design two structural pruning-based adversarial sample privacy protections, in which the user obtains the perturbed data through the pruned deep learning model. Extensive experiments are conducted on four datasets, and the results demonstrate the effectiveness of our adversarial sample privacy protection based on structural pruning.

18 April 2022 in Security and Communication Networks
Verified
Journal Article
Open access
PDF file
GXGuangxu Xie
Guangxu Xie
Qingqi PeiQingqi Pei
Qingqi Pei
An adversarial example is the weakness of the machine learning (ML), and it can be utilized as the tool to defend against the inference attacks launched by ML classifiers. Jia et al. proposed MemGuard, which applied the idea of adversarial example to defend against membership inference attack. In a membership inference attack, the attacker attempts to infer whether a particular sample is in the training set of the target classifier, which may be a software or a service whose model parameters are unknown to the attacker. MemGuard does not tamper the training process of the target classifier, meanwhile achieving better tradeoff between the privacy and utility loss. However, many defenses of the adversarial example have been proposed, which decreases the effectiveness of the adversarial example. Inspired by the defenses of the adversarial example, we try to attack the MemGuard. As a result, we utilize the nonlocal-means method to do the attack by using the inherent relationship between neighbor entries to remove the added noise. Due to the low dimensionality of the confidence score vector, our attack avoids the high computation overhead of the nonlocal-means method. Besides, we use practical datasets to test our attack, and the experimental results demonstrate the effectiveness of our attack.


2 June 2026 in Electronics
Verified
Journal Article
Open access
PDF file
XJXuehuan Jiang
Xuehuan Jiang
XLXiao Liu
Xiao Liu
GXGuangxu Xie
Guangxu Xie
Haibo HuangHaibo Huang
Haibo Huang
Qingqi PeiQingqi Pei
Qingqi Pei
ZWZhixue Wang
Zhixue Wang
The integration of blockchain technology into the Internet of Things (IoT) offers a decentralized paradigm for data integrity. However, the emergence of 51% attacks—driven by hashrate concentration—threatens the foundational trust of these resource-constrained networks. In resource-constrained IoT-enabled blockchain environments, mining-power asymmetry and limited governance capability may amplify the impact of strategic attacks. These characteristics motivate the need to analyze long-term adversarial behavior and governance effectiveness under repeated interactions. This paper develops a threshold-based analytical framework that integrates a single-stage decision model and a multi-stage discounted decision model to analyze 51% attack decisions and governance effects in asymmetric blockchain mining environments. We characterize the interaction between competing mining pools as a multi-stage game, integrating key parameters such as the discount factor of future utility and recovery penalty cycles. Our analysis demonstrates that a multi-stage framework creates a “long-term deterrent effect” where the net present value of potential future losses outweighs the immediate gains of hashrate abuse. analytical results indicate that the strategic threshold for launching an attack is highly sensitive to the duration of punitive measures and the accuracy of IoT-based anomaly detection. The results provide useful insights into the design of governance and incentive mechanisms for blockchain systems deployed in resource-constrained and heterogeneous environments.

2 June 2026 in IEEE Transactions on Services Computing
Verified
Journal Article
Closed access
GXGuangxu Xie
Guangxu Xie
YXYang Xiao
Yang Xiao
Qingqi PeiQingqi Pei
Qingqi Pei
HHHaibo Huang
Haibo Huang
An attacker can determine if a specific input belongs to a deep learning model's training set by analyzing the complete confidence vector output, known as a membership inference attack. To counter this type of attack, a common defense strategy is to add adversarial noise to the confidence vector to enhance the model's resilience. However, existing research indicates that defenses against adversarial examples may introduce new security risks to membership inference defenses via adversarial examples. Against this backdrop, this paper proposes a more robust adversarial example defense strategy. By generating adversarial examples with distributions similar to normal samples, we can reduce the impact of distributional differences on the defense model's security. Leveraging normalizing flow, adding noise to the hidden layer of a flow model trained on normal samples generates adversarial examples that resemble normal ones, enhancing defense robustness. Additionally, limiting the information accessible to the attack model further strengthens robustness. To accelerate convergence, a bidirectional mean update method is employed. The proposed strategy demonstrates effectiveness not only in defending against membership inference attacks but also in mitigating attribute inference attacks. Finally, experiments on real-world datasets validate the effectiveness of the proposed strategy.