Prof. Dr. Xin Wang, Qilu University of Technology, China
Prof. Dr. Xin Wang is a distinguished scholar in Distributed AI and Federated Learning, currently serving as a Professor at Shandong Computer Science Center, Qilu University of Technology. With a Ph.D. in Control Science and Engineering from Zhejiang University, he has contributed significantly to AI Security, Privacy, and LLM Security. Dr. Wang has led multiple national research projects and received prestigious honors, including the Taishan Scholars Award and the Shandong Provincial Science and Technology Progress Award. His work integrates AI with secure computing, enhancing privacy protection and optimization in collaborative learning systems.
🌍 Professional Profile:
Google Scholar
🏆 Suitability for Award
Dr. Xin Wang’s outstanding contributions to Distributed AI, Federated Learning, and AI Security make him a strong candidate for the Best Researcher Award. As a leader in AI-driven security frameworks, he has spearheaded national-level projects focusing on privacy-preserving AI and secure learning models. His research bridges theory with practical applications, enhancing security in multi-agent and industrial IoT systems. Recognized for his high-impact publications and award-winning research, Dr. Wang’s innovations in cryptographic function identification and UAV data collection optimization demonstrate exceptional originality and real-world relevance, solidifying his place as a leader in computational intelligence and AI security.
🎓 Education
- Ph.D. in Control Science and Engineering (2015-2020) – Zhejiang University, supervised by Prof. Peng Cheng & Prof. Jiming Chen, specializing in AI Security and Distributed Intelligence.
- Visiting Scholar in Information Security (2018-2019) – Tokyo Institute of Technology, mentored by Prof. Hideaki Ishii, focusing on cryptographic vulnerabilities and federated learning security.
His multidisciplinary training across AI, security, and automation has positioned him at the forefront of cutting-edge computational research.
💼 Experience
- Professor (2024–Present) – Shandong Computer Science Center, Qilu University of Technology.
- Associate Professor (2020–2024) – Shandong Computer Science Center, leading research on privacy protection in collaborative AI.
- Project PI in National Natural Science Foundation of China (2025-2027) – Developing privacy-preserving defense mechanisms for federated learning.
- Project PI in National Key Research and Development Program (2021-2024) – Developing AI-driven meta-services for cloud-based industrial manufacturing.
- Visiting Scholar (2018-2019) – Tokyo Institute of Technology, conducting security research on cryptographic vulnerabilities in multi-agent IoT systems.
🏅 Awards and Honors
- Taishan Scholars Award (2024) 🏅 – Recognized for research excellence in AI security and distributed systems.
- Leader of Youth Innovation Team (2022) 🚀 – Acknowledged for driving innovation in Shandong Higher Education Institutions.
- Second Prize, Shandong Provincial Science and Technology Progress Award (2022) 🏆 – Contributions to federated learning and privacy-preserving AI.
- Best Paper Award, CCSICC’21 📄 – Vulnerability Analysis for IoT Devices in Multi-Agent Systems.
- Best Paper Award, ICAUS’24 ✈️ – Optimized Data Collection for UAVs in Industrial IoT Environments.
🔬 Research Focus
Dr. Wang specializes in Distributed AI, Federated Learning, and AI Security & Privacy. His research integrates cryptographic techniques, optimization algorithms, and adversarial defenses to improve the security of collaborative learning models. He has pioneered LLM security frameworks to safeguard against data leakage and adversarial attacks. His work extends into privacy-preserving AI for multi-agent IoT systems and UAV data collection efficiency. Through national projects, he has developed secure meta-services for cloud computing, advancing the field of intelligent automation and resilient AI architectures for real-world deployment in cyber-physical systems and industrial environments.
📊 Publication Top notes:
-
Title: Privacy-Preserving Distributed Machine Learning via Local Randomization and ADMM Perturbation
-
Title: Privacy-Preserving Collaborative Computing: Heterogeneous Privacy Guarantee and Efficient Incentive Mechanism
-
Title: Differentially Private Maximum Consensus: Design, Analysis and Impossibility Result
-
Title: Dynamic Privacy-Aware Collaborative Schemes for Average Computation: A Multi-Time Reporting Case
-
Title: Leveraging UAV-RIS Reflects to Improve the Security Performance of Wireless Network Systems