Prof. Xiangyun Tang holds a Ph.D. in Cyberspace Security from the Beijing Institute of Technology, Beijing, China, where he studied from September 2016 to June 2022. His doctoral research focused on “Secure and Trustworthy Distributed Machine Learning,” supervised by Prof. Liehuang Zhu and Prof. Meng Shen, and he achieved an impressive GPA of 3.83/4.00. He also holds a Bachelor of Engineering in Computer Science from Minzu University of China, completed in June 2016, with a GPA of 3.68/4.00. His strong academic foundation underscores his expertise in cybersecurity and distributed systems.
Experience
Prof. Xiangyun Tang has accumulated extensive experience in academia, research, and industry. As a Ph.D. candidate at the Beijing Institute of Technology, he conducted groundbreaking research in secure and trustworthy distributed machine learning under the guidance of Profs. Liehuang Zhu and Meng Shen. During his tenure as a Machine Learning Engineer at Tencent Technology Inc., he developed real-time forwarding prediction models for cascade graphs and sentiment quantification solutions using Graph Neural Networks. Additionally, he has participated in various funded projects, including privacy-preserving federated learning systems and blockchain-based collaborative learning mechanisms, where he contributed to system design and implementation. Prof. Tang has also provided professional services as a reviewer for top-tier journals like the IEEE Internet of Things J
Research Interests
Prof. Xiangyun Tang’s research interests lie at the intersection of machine learning security, data privacy preservation, and applied cryptography. He focuses on designing robust privacy-preserving verifiability systems to enhance the security of federated learning, effectively defending against malicious participants. His work leverages advanced cryptographic techniques, including zero-knowledge proofs, homomorphic encryption, and secret sharing, to ensure data privacy and system integrity. Prof. Tang’s research aims to address critical challenges in secure collaborative learning and develop innovative solutions that integrate privacy and performance in distributed machine learning environments.
Skills
Prof. Xiangyun Tang possesses a diverse skill set that bridges advanced cryptographic techniques and practical applications in machine learning security. His expertise includes designing privacy-preserving systems utilizing zero-knowledge proofs, homomorphic encryption, and secret sharing to ensure secure and trustworthy distributed machine learning. He is proficient in developing robust algorithms for federated learning, enabling secure data sharing and collaborative training across decentralized environments. Additionally, Prof. Tang has extensive experience in sentiment quantification, real-time data analysis on cascade graphs, and implementing secure systems for software-defined networks and blockchain-based applications. His technical acumen is complemented by strong problem-solving skills and a commitment to advancing data privacy and cybersecurity.
Publications
Privacy-Preserving Support Vector Machine Training over Blockchain-Based Encrypted IoT Data in Smart Cities
- Authors: M. Shen, X. Tang, L. Zhu, X. Du, M. Guizani
- Journal: IEEE Internet of Things Journal
- Volume: 6 (5), Pages: 7702-7712
- Cited By: 465
- Year: 2019
Privacy-Preserving DDoS Attack Detection Using Cross-Domain Traffic in Software Defined Networks
- Authors: L. Zhu, X. Tang, M. Shen, X. Du, M. Guizani
- Journal: IEEE Journal on Selected Areas in Communications
- Volume: 36 (3), Pages: 628-643
- Cited By: 121
- Year: 2018
Secure SVM Training over Vertically-Partitioned Datasets Using Consortium Blockchain for Vehicular Social Networks
- Authors: M. Shen, J. Zhang, L. Zhu, K. Xu, X. Tang
- Journal: IEEE Transactions on Vehicular Technology
- Volume: 69 (6), Pages: 5773-5783
- Cited By: 87
- Year: 2019
Privacy-Preserving Machine Learning Training in IoT Aggregation Scenarios
- Authors: L. Zhu, X. Tang, M. Shen, F. Gao, J. Zhang, X. Du
- Journal: IEEE Internet of Things Journal
- Volume: 8 (15), Pages: 12106-12118
- Cited By: 33
- Year: 2021
Pile: Robust Privacy-Preserving Federated Learning via Verifiable Perturbations
- Authors: X. Tang, M. Shen, Q. Li, L. Zhu, T. Xue, Q. Qu
- Journal: IEEE Transactions on Dependable and Secure Computing
- Volume: 20 (6), Pages: 5005-5023
- Cited By: 28
- Year: 2023
Blockchains for Artificial Intelligence of Things: A Comprehensive Survey
- Authors: M. Shen, A. Gu, J. Kang, X. Tang, X. Lin, L. Zhu, D. Niyato
- Journal: IEEE Internet of Things Journal
- Volume: 10 (16), Pages: 14483-14506
- Cited By: 27
- Year: 2023
Secure and Trusted Collaborative Learning Based on Blockchain for Artificial Intelligence of Things
- Authors: X. Tang, L. Zhu, M. Shen, J. Peng, J. Kang, D. Niyato, A. A. Abd El-Latif
- Journal: IEEE Wireless Communications
- Volume: 29 (3), Pages: 14-22
- Cited By: 24
- Year: 2022
Secure Semantic Communications: Challenges, Approaches, and Opportunities
- Authors: M. Shen, J. Wang, H. Du, D. Niyato, X. Tang, J. Kang, Y. Ding, L. Zhu
- Journal: IEEE Network
- Cited By: 15
- Year: 2023
Fully Exploiting Cascade Graphs for Real-Time Forwarding Prediction
- Authors: X. Tang, D. Liao, W. Huang, L. Zhu, M. Shen, J. Xu
- Conference: AAAI 2021 Conference
- Cited By: 36
- Year: 2021
When Homomorphic Cryptosystem Meets Differential Privacy: Training Machine Learning Classifier with Privacy Protection
- Authors: X. Tang, L. Zhu, M. Shen, X. Du
- Platform: arXiv preprint
- arXiv ID: arXiv:1812.02292
- Cited By: 11
- Year: 2018
Conclusion
Prof. Xiangyun Tang’s extensive contributions to privacy-preserving machine learning, applied cryptography, and data security establish him as an exceptional candidate for the Research for Best Researcher Award. His innovative research, industry experience, academic service, and numerous accolades collectively make him highly deserving of this recognition.