Xiao Yang

Xiao Yang

Auto-generated profile, based on publicly available information

Xiao Yang

School of Computer Science, Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
26 November 2019 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
XYXiao Yang
Xiao Yang
MDMianxiong Dong
Mianxiong Dong
XCXiuzhen Chen
Xiuzhen Chen
KOKaoru Ota
Kaoru Ota
Open social network (OSN) plays a more significant role in information propagation through the rapid developing of information technology. Since information diffusion is an essential process happens in OSN, it has been studied in many studies. Several models have been proposed to infer the diffusion process and reproduce diffusion network. However, these methods have two critical problems: 1) ignoring the effects of user social characteristics and 2) inaccuracy resulted from calculating the influence of different features independently. To address these limitations, a diffusion inferring method based on a recommender system (DIM-SPTF) was proposed. The DIM-SPTF method considers the propagation process between the users as the recommendation process of information and employs a recommender system to infer the propagation relationship. Through determining the propagation relations among all users in the observed topic data set, an information diffusion network can be finally obtained. Experimental results show that DIM-SPTF leads to improvements in performance compared with the state-of-the-art methods.

11 March 2025 in IEEE Open Journal of Vehicular Technology
Verified
Journal Article
Open access
XYXiao Yang
Xiao Yang
Gaolei LiGaolei Li
Gaolei Li
KZKai Zhou
Kai Zhou
Jianhua LiJianhua Li
Jianhua Li
XLXingqin Lin
Xingqin Lin
YLYuchen Liu
Yuchen Liu
Advances in Graph Neural Networks (GNNs) have substantially enhanced Vehicular Networks (VNs) across primary domains, encompassing traffic forecasting and management, route optimization and algorithmic planning, and cooperative driving. Despite the boosts of the GNN for VNs, recent research has empirically demonstrated its potential vulnerability to backdoor attacks, wherein adversaries integrate triggers into inputs to manipulate GNNs to generate adversary-premeditated malicious outputs (e.g., misclassification of vehicle actions or traffic signals). This susceptibility is attributable to adversarial manipulation attacks targeting the training process of GNN-based VN systems. Although there is a rapid increase in research on GNN backdoors, systematic surveys within this domain remain lacking. To bridge this gap, we present the first survey dedicated to GNN backdoors. We start with outlining the fundamental definition of GNNs, followed by the detailed summarization and categorization of current GNN backdoors and countermeasures based on their technical features and application scenarios. Subsequently, an analysis of the applicability paradigms of GNN backdoors is conducted, and prospective research trends are presented. Unlike prior surveys on vision-centric backdoors, we uniquely investigate GNN-oriented backdoor attacks in VNs, which aims to explore attack surfaces across spatiotemporal vehicular graphs and provide insights to security research.

24 January 2025 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
XYXiao Yang
Xiao Yang
Gaolei LiGaolei Li
Gaolei Li
JWJun Wu
Jun Wu
KZKai Zhou
Kai Zhou
Jianhua LiJianhua Li
Jianhua Li
WYWu Yang
Wu Yang
Edge-Level Graph Learning System (EGLS) exhibits diverse applicability in flow prediction, route planning, and accident forecasting. Existing EGLS studies extremely stress absolute fairness and impartiality for all users, resultantly depriving its flexibility and humanity in addressing special circumstances and rendering the privilege authorization for exceptional responses challenging to achieve. To address this limitation, we present BackPriv, the first privilege authorization methodology enabling regulable privilege assignment or revocation in EGLS. Specifically, it is achieved through a creative edge backdoor mechanism, wherein the edge training samples are poisoned via user-specific privilege tokens to induce privilege outputs from the well-trained EGLS for authorized users. Moreover, related EGLS regulating strategies were proposed to dynamically realize the addition and revocation of user privileges by system retraining to guarantee privilege control in EGLS. Additionally, a Graph Mutual Information-based adaptive privilege token generation method is introduced to reduce the impact of privilege authorization on normal inputs and augment authorization functionality. Based on experiments with multiple real-world datasets, BackPriv demonstrates high success rates of privilege authorization under various scenarios ( 100%) and exerts minimal impact on normal task performance for regular inputs (mean accuracy drop 0.32%).

19 June 2025 in Information Fusion
Verified
Journal Article
Closed access
XYXiao Yang
Xiao Yang
Gaolei LiGaolei Li
Gaolei Li
KZKai Zhou
Kai Zhou
YLYuni Lai
Yuni Lai
JLJianhua Li
Jianhua Li

31 October 2025 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
XYXiao Yang
Xiao Yang
YLYuni Lai
Yuni Lai
Gaolei LiGaolei Li
Gaolei Li
Jun WuJun Wu
Jun Wu
KZKai Zhou
Kai Zhou
MCMingzhe Chen
Mingzhe Chen
Semantic Communication (SC) achieves meaning transmission instead of bitstreams by deep semantic encoding-decoding. Since the encoder-decoder contains sensitive and proprietary knowledge, its illicit leakage infringes commercial benefits and copyright, which warrants corresponding protection. However, current SC security paradigms narrowly emphasize transmission data protection while neglecting encoding knowledge safeguarding. To bridge this gap, we present SemanAegis, the first SC knowledge protection framework. SemanAegis integrates a built-in-system access control mechanism that remains effective even if the system is stolen, ensuring that unauthorized access attempts yield unacceptable low-fidelity outputs, while credential-embedded inputs from authorized entities are met with accurate responses. Specifically, we establish access control through backdoor implantation, whereby only inputs embedded with credentials activate the backdoor and access system, while source inputs are constrained to generate erroneous results. Moreover, we adopt a synthesizer to generate imperceptible credentials, thus guaranteeing their confidentiality. Additionally, a dedicated contrastive learning strategy is implemented to accelerate the convergence of backdoor implanting. Empirical evaluations across SC systems and benchmark datasets demonstrate SemanAegis precisely rejects unauthorized inputs, effectively mitigates knowledge extractions, and consistently preserves SC regular functionality.

19 January 2026 in IEEE Wireless Communications Letters
Verified
Journal Article
Closed access
XYXiao Yang
Xiao Yang
YHYuanhang He
Yuanhang He
Gaolei LiGaolei Li
Gaolei Li
Jianhua LiJianhua Li
Jianhua Li
YXYang Xu
Yang Xu
MCMingzhe Chen
Mingzhe Chen
Semantic Communication (SC) codecs contain valuable intellectual property, but current security is ineffective against model piracy. To address this, we propose SemGuard, an intrinsic trusted access framework that embeds a backdoor within the SC codec. Legitimate users use a credential generator to embed sample-specific credentials into inputs, activating the backdoor for seamless transmission. Conversely, unauthorized inputs lacking this credential are deliberately processed into anomalous outputs. This backdoor is implanted via a regularized joint training process. Even if the model is extracted, it remains functionless without credentials, effectively deterring illegitimate access without sacrificing efficiency, and preserving defensive efficacy in adversarial settings.