Mingyue Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Mingyue Li has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
- Ruizhong Du
School of Cyber Security and Computer, Hebei University, Baoding, Hebei, China
18 shared publications - Chunfu Jia
Nankai University
17 shared publications - Guanxiong Ha
Nankai University
7 shared publications - Ruizhong Du
Hebei University
5 shared publications - Wei Shao
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
4 shared publications - Xiaoyun Guang
Hebei University
4 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (12) , 22590-22604
LMCR: Lossless Multi-Probe Cross-Modal Retrieval With Privacy Preservation
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (12) , 22590-22604
LMCR: Lossless Multi-Probe Cross-Modal Retrieval With Privacy Preservation
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4954-4963
Adv-Tokens: Target-Aware Residual Identity Token Injection for Transferable Facial Privacy Protection
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4954-4963
Open AccessAdv-Tokens: Target-Aware Residual Identity Token Injection for Transferable Facial Privacy Protection
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4944-4953
TailorProtect: Meta-learning-based Tailored Text-enhanced Facial Privacy Protection
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4944-4953
Open AccessTailorProtect: Meta-learning-based Tailored Text-enhanced Facial Privacy Protection
- 8 October 2026
- Published by Springer Nature
- p. 264-278
Deep Multi-scale Graph Synthesis with Community Information Under Differential Privacy
- 8 October 2026
- Published by Springer Nature
- p. 264-278
Deep Multi-scale Graph Synthesis with Community Information Under Differential Privacy
- Open Access
- 20 August 2026
- Published by Elsevier in SSRN Electronic Journal
An Intelligent Topology Control Framework for UWSNs Based on Degree Constraints and Multi-Dimensional Link Utility Assessment
Underwater wireless sensor networks (UWSNs) face severe marine constraints, and existing topology control algorithms lack the intelligent decision-making capabilities to simultaneously maximize network lifetime and topological robustness. To address this trade-off, this paper proposes an intelligent Degree Constraint-based Multidimensional Link Utility Adaptation (DC-MUA) expert framework. DC-MUA integrates three core adaptive mechanisms. First, spatial density-based dynamic degree constraints intelligently mitigate channel congestion. Second, an adaptive link replacement strategy prevents localized fragmentation and ensures global connectivity. Third, an energy-balanced load protection expert mechanism distributes communication loads uniformly across the network. Extensive simulations demonstrate the strong resilience and intelligent self-healing capabilities of DC-MUA under varying densities and extreme conditions, including random node failures and malicious attacks. Specifically, in high-density scenarios, DC-MUA extends the network lifetime by up to 66.7\% compared to the EDNPM algorithm, and improves data throughput by approximately 23\% over the EEUMC approach. Ultimately, the proposed intelligent framework significantly reduces energy consumption variance while substantially enhancing system robustness and overall network efficiency.
- 20 August 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAn Intelligent Topology Control Framework for UWSNs Based on Degree Constraints and Multi-Dimensional Link Utility Assessment
Underwater wireless sensor networks (UWSNs) face severe marine constraints, and existing topology control algorithms lack the intelligent decision-making capabilities to simultaneously maximize network lifetime and topological robustness. To address this trade-off, this paper proposes an intelligent Degree Constraint-based Multidimensional Link Utility Adaptation (DC-MUA) expert framework. DC-MUA integrates three core adaptive mechanisms. First, spatial density-based dynamic degree constraints intelligently mitigate channel congestion. Second, an adaptive link replacement strategy prevents localized fragmentation and ensures global connectivity. Third, an energy-balanced load protection expert mechanism distributes communication loads uniformly across the network. Extensive simulations demonstrate the strong resilience and intelligent self-healing capabilities of DC-MUA under varying densities and extreme conditions, including random node failures and malicious attacks. Specifically, in high-density scenarios, DC-MUA extends the network lifetime by up to 66.7\% compared to the EDNPM algorithm, and improves data throughput by approximately 23\% over the EEUMC approach. Ultimately, the proposed intelligent framework significantly reduces energy consumption variance while substantially enhancing system robustness and overall network efficiency.
- 17 July 2026
- Published by Springer Nature
- p. 468-477
LPPITR: A Lightweight Privacy-Preserving Image-Text Cross-Modal Retrieval in IoT
- 17 July 2026
- Published by Springer Nature
- p. 468-477
LPPITR: A Lightweight Privacy-Preserving Image-Text Cross-Modal Retrieval in IoT
- 13 July 2026
- Published by Springer Nature
- p. 101-111
A Highly Accurate Leakage Abuse Attack Using Refine-Subgraph Against DSSE
- 13 July 2026
- Published by Springer Nature
- p. 101-111
A Highly Accurate Leakage Abuse Attack Using Refine-Subgraph Against DSSE
- 6 June 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 201
Transferable adversarial attacks against face recognition via region-focused distillation
- 6 June 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 201
Transferable adversarial attacks against face recognition via region-focused distillation
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-18
STDFL: A Spatio-Temporal-Aware Dynamic Federated Learning Framework for Spatial Crowdsourcing
Spatial Mobile Crowdsourcing (SMC) faces the dual challenge of ensuring privacy while managing dynamic, Non-IID spatio-temporal data. While Federated Learning (FL) offers a privacy-preserving solution, traditional aggregation suffers from severe model drift due to evolving spatio-temporal contexts. Furthermore, existing approaches often decouple prediction from scheduling, failing to translate predictive insights into tangible task allocation efficiency. To address these challenges, we propose STDFL, a prediction-driven dynamic framework tailored for SMC. It features a hierarchical architecture combining client-side lightweight models for micro-patterns and a server-side Transformer for global dependencies. To mitigate drift, our Dynamic Spatio-Temporal Perceiving Aggregation adaptively weights updates based on spatial similarity and temporal freshness. For privacy, we integrate client-level $(\epsilon , \delta )$-Differential Privacy to ensure formal protection. Finally, we introduce a Prediction-Driven Scheduler (PDS) that leverages predictive potentials for bipartite matching, theoretical analysis and stress tests confirm PDS achieves linear scalability and zero policy training cost, offering a superior real-time deployment trade-off compared to RL approaches. Experiments on Chengdu and Nanjing datasets show STDFL significantly outperforms SOTA baselines in efficiency and fairness,while achieving near-centralized prediction accuracy under rigorous privacy guarantees and effectively bridging the utility–privacy trade-off in spatial crowdsourcing.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-18
STDFL: A Spatio-Temporal-Aware Dynamic Federated Learning Framework for Spatial Crowdsourcing
Spatial Mobile Crowdsourcing (SMC) faces the dual challenge of ensuring privacy while managing dynamic, Non-IID spatio-temporal data. While Federated Learning (FL) offers a privacy-preserving solution, traditional aggregation suffers from severe model drift due to evolving spatio-temporal contexts. Furthermore, existing approaches often decouple prediction from scheduling, failing to translate predictive insights into tangible task allocation efficiency. To address these challenges, we propose STDFL, a prediction-driven dynamic framework tailored for SMC. It features a hierarchical architecture combining client-side lightweight models for micro-patterns and a server-side Transformer for global dependencies. To mitigate drift, our Dynamic Spatio-Temporal Perceiving Aggregation adaptively weights updates based on spatial similarity and temporal freshness. For privacy, we integrate client-level $(\epsilon , \delta )$-Differential Privacy to ensure formal protection. Finally, we introduce a Prediction-Driven Scheduler (PDS) that leverages predictive potentials for bipartite matching, theoretical analysis and stress tests confirm PDS achieves linear scalability and zero policy training cost, offering a superior real-time deployment trade-off compared to RL approaches. Experiments on Chengdu and Nanjing datasets show STDFL significantly outperforms SOTA baselines in efficiency and fairness,while achieving near-centralized prediction accuracy under rigorous privacy guarantees and effectively bridging the utility–privacy trade-off in spatial crowdsourcing.
- Open Access
- 27 February 2026
- Published by Elsevier in SSRN Electronic Journal
AUV Data Collection Algorithm Optimization Based on UIoT Dynamic Topology Characteristics
Mobile Underwater Internet of Things (UIoT) has become one of the pivotal technologies in the advancement of smart oceans monitoring systems, with autonomous underwater vehicles (AUVs) offering a highly promising way for collecting data from mobile sensor nodes. In Mobile UIoT, the mobility of sensor nodes leads to dynamic changes in network topology, making it difficult for the network to form stable clusters. The selection and position of cluster-head nodes will also dynamically change, which increases the difficulty of AUV collecting cluster-head nodes data and further increases data collection delay. To overcome these above difficulties, AUVs are employed as mobile edge devices for collecting data from nodes within the UIoT. In addition, a data collection algorithm orientated for dynamic network topology (DCADNT) is proposed in this paper, which includes three phases: dynamic clustering, dynamic transmission, and dynamic data collection. DCADNT not only considers the impact of dynamic topology on data collection, but also takes into account the impact of propagation delay. By calculating the packet delivery probability based on propagation delay, the reliability of data transmission can be effectively guaranteed. The performance of DCADNT is evaluated by extensive simulations and the compared results with other typical data collection algorithms are given, which demonstrate that DCADNT effectively reduces data collection delay and improves packet collection rate.
- 27 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAUV Data Collection Algorithm Optimization Based on UIoT Dynamic Topology Characteristics
Mobile Underwater Internet of Things (UIoT) has become one of the pivotal technologies in the advancement of smart oceans monitoring systems, with autonomous underwater vehicles (AUVs) offering a highly promising way for collecting data from mobile sensor nodes. In Mobile UIoT, the mobility of sensor nodes leads to dynamic changes in network topology, making it difficult for the network to form stable clusters. The selection and position of cluster-head nodes will also dynamically change, which increases the difficulty of AUV collecting cluster-head nodes data and further increases data collection delay. To overcome these above difficulties, AUVs are employed as mobile edge devices for collecting data from nodes within the UIoT. In addition, a data collection algorithm orientated for dynamic network topology (DCADNT) is proposed in this paper, which includes three phases: dynamic clustering, dynamic transmission, and dynamic data collection. DCADNT not only considers the impact of dynamic topology on data collection, but also takes into account the impact of propagation delay. By calculating the packet delivery probability based on propagation delay, the reliability of data transmission can be effectively guaranteed. The performance of DCADNT is evaluated by extensive simulations and the compared results with other typical data collection algorithms are given, which demonstrate that DCADNT effectively reduces data collection delay and improves packet collection rate.