Xiaoguang Chen

Xiaoguang Chen

Auto-generated profile, based on publicly available information

Xiaoguang Chen

Macau Institute of Systems Engineering, Macau University of Science and Technology, Macao, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
28 June 2022 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
ZJZhiyang Ju
Zhiyang Ju
FZFeifei Zhang
Feifei Zhang
XLXiang Li
Xiang Li
XCXiaoguang Chen
Xiaoguang Chen
JHJinpeng Han
Jinpeng Han
MYManzhi Yang
Manzhi Yang
Recent advances in attack/anomaly detection and resilience strategies for connected and automated vehicles (CAVs) are reviewed from vehicle dynamics and control perspective. Compared to traditional vehicles, CAVs are featured in the increasing number of perception sensors, advanced intra-vehicle communication technologies, capabilities of driving automation and connectivity between single vehicles. These features bring about safety issues which are not encountered in traditional vehicle systems. One main type of these issues is the attack or anomaly launched onto the perception sensors and the communication channels. With such a consideration, this survey summarizes and reviews the existing results on attack/anomaly detection and resilience of CAVs in control frameworks. This paper reviews the results according to the positions at which the attacks/anomalies occur. These positions are divided into three categories, namely, intra-vehicle communication network, perception sensors and inter-vehicle communication network. From this perspective, the recent attack/anomaly detection and resilience results are reviewed according to different positions attacked. After reviewing existing results, some potential research directions and challenges are identified.

14 August 2023 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
JHJinpeng Han
Jinpeng Han
ZJZhiyang Ju
Zhiyang Ju
XCXiaoguang Chen
Xiaoguang Chen
MYManzhi Yang
Manzhi Yang
FZFeifei Zhang
Feifei Zhang
RHRouxing Huai
Rouxing Huai
With features of collaborative interaction and autonomous decision-making, connected and autonomous vehicles (CAVs) offer a viable solution for a sustainable and efficient future of transportation. However, with the development of CAVs, questions have been raised about weaknesses in cybersecurity and autonomous driving capabilities. In particular, CAVs provide new opportunities for cyberattackers, posing a significant threat to future road and vehicle data security. Therefore, this paper provides a comprehensive analysis of the cybersecurity environment of CAVs. First, we propose a systematic classification of six security threats from cybersecurity principles: false data, information theft, privilege escalation, block communication, and time delay. We review the cybersecurity environment of CAVs from a lifecycle perspective, covering aspects from development to accident, and present the existing cybersecurity countermeasures. These involve security standards designation, verification and validation of vehicle networks, resilient strategies for self-defined driving, and attack detection and digital forensics. Finally, based on our systematic review, we propose a conceptual vehicle security operations center (VSOC) framework that provides valuable inspiration and references for future research and industrial applications for CAVs cybersecurity.

22 December 2022 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Open access
JHJinpeng Han
Jinpeng Han
MYManzhi Yang
Manzhi Yang
XCXiaoguang Chen
Xiaoguang Chen
HLHongtao Liu
Hongtao Liu
XXxxxx xxxx
xxxx xxxx
XMXiaobo Ma
Xiaobo Ma
The metaverse, as an instance of cyber–physical–social systems (CPSS) that originates in cyber–physical systems (CPS), features growing complexity, and diversity in terms of functionalities, as well as the exponentially increasing demand in network bandwidth and computational resources, thereby leading to exaggerated security threats. However, compared with the extensive attention received by the metaverse, solutions defending against the threats have not kept pace. A major obstacle to such solutions is virtuality–reality-synthesized threats. Therefore, it is imperative to design new paradigms to defend the metaverse effectively. In this article, we advance a parallel system, dubbed ParaDefender, to defend the metaverse against emerging new threats effectively. Inspired by parallel intelligence, ParaDefender comprises artificial cyberspace, computational experiments, and parallel execution. The basic idea is to make artificial and real cyberspaces executed in parallel to mutually guide each other for enhanced security, wherein the parallel execution is scenario driven in the sense that the scenarios originate from all possible spatial–temporal combinations of security threats in the metaverse. We also demonstrate how to land ParaDefender onto real-world applications, including the Industrial Internet of Things (IIoT) security operation application in the industrial metaverse, and the social governance application.

16 September 2024 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
XCXiaoguang Chen
Xiaoguang Chen
WCWenyuan Cao
Wenyuan Cao
CLChen Lili
Chen Lili
JHJinpeng Han
Jinpeng Han
MYManzhi Yang
Manzhi Yang
FWFei-Yue Wang
Fei-Yue Wang
Social manufacturing has significantly advanced the industrial Internet of Things (IIoT), integrating information technology and operation technology to enhance production efficiency and quality, and to foster new business models. This integration, however, introduces novel risks, including advanced persistent threats, which demand robust security measures to safeguard IIoT systems. This article proposes an iCyberGuard game model, tailored for IIoT environments, designed to imitate the cyber and physical attacks for information and operation technologies. Then, we used a reinforcement learning algorithm to compute the optimal strategy. We conducted comprehensive simulation experiments, which demonstrate that our model the strategic interactions between attackers and defenders. Participants are enabled to learn adaptively, discerning optimal strategies based on the intelligence of their adversaries. Finally, we explain the practical significance of the best strategy of defenders or attackers, and how users can rely on these best strategies to strengthen the security performance of the network.

18 July 2024 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
MYManzhi Yang
Manzhi Yang
JZJian Zhang
Jian Zhang
LLLiyuan Lin
Liyuan Lin
JHJinpeng Han
Jinpeng Han
XCXiaoguang Chen
Xiaoguang Chen
FWFei-Yue Wang
Fei-Yue Wang
As a challenge of practical significance, fraud detection has great potential for telecom fraud prevention, economic crime prevention, and personal property preservation. Fraudulent activities are always buried in massive regular transactions, making it hard to find them. Traditional rule-based approaches need multiple domain-specific rules and multistep verification, which limits their transferability and efficiency. Machine learning-based methods might ignore the intricate interactions or the temporal relations among accounts. Meanwhile, the lack of sufficient manual labels restricts their performance. To overcome the above limitations, we present a multipattern integrated network (MPIN) in this article to identify fraudulent accounts in transaction networks. Specifically, MPIN considers the interactions among nodes from three perspectives: inflows, outflows, and their mutual influences. To learn the behavior pattern of each node, MPIN first applies an attention mechanism to integrate the short-term information and then learns the long-term patterns by aggregating multiple short-term patterns. Behavior patterns from different perspectives together with long short-term modeling enable the model to precisely distinguish fraudulent accounts from the normal ones. Moreover, contrastive pretraining with temporal consistency and local tightness guarantee is adopted to alleviate the label sparsity issue and provide the model with low-variance performance. We conducted experiments on two real-world transaction networks, and the results showed the effectiveness of MPIN compared with five state-of-the-art baselines.

1 July 2017
Verified
Conference Paper
Closed access
XCXiaoguang Chen
Xiaoguang Chen
JTJunyong Tao
Junyong Tao
Guanghan BaiGuanghan Bai
Guanghan Bai
YZYunan Zhang
Yunan Zhang
A general method for the reliability evaluation of multistate networks is using minimal path vectors (d-MPs for short). Most reported works on generating d-MPs are based on minimal paths (MPs for short). Currently, all reported MP-based algorithms generate duplicated d-MPs during the search process and additional recursive comparison is required to remove those duplications. However, the number of duplications increases substantially with the size of network. Thus, a more efficient algorithm is needed to search for all d-MPs without duplications. In this study, we proposed an improved algorithm based on the breadth-first search to search for d-MPs without duplications. The mechanism on generating duplicated d-MPs is investigated. A novel approach is incorporated into the existing algorithm to generate the d-MPs without duplications. Through computational experiments, it is found that the proposed algorithm is more efficient than existing algorithms for finding all d-MPs.