Feng Li

Feng Li is a Professor in the Department of Computer and Information Technology at Indiana University - Purdue University Indianapolis (IUPUI), School of Science. He received his PhD from Florida Atlantic University in 2009 and has since established himself as a leading researcher in network security, wireless networks, and privacy-preserving technologies.

His research interests span across multiple domains in computer science, with a primary focus on Network Security, Wireless and Mobile Ad-hoc Networks, Federated Learning Security, Differential Privacy, and Social Network Analysis. Dr. Li's work consistently addresses critical challenges in securing distributed systems while preserving user privacy, with applications ranging from social networks to edge computing environments. His research methodology often combines theoretical frameworks with practical implementations, resulting in solutions that balance security, privacy, and system performance.

Dr. Li's publication record reveals a strong trajectory in addressing evolving security challenges in distributed systems. His recent work has focused on securing federated learning systems against sophisticated attacks like backdoors, developing privacy-preserving techniques for social networks using differential privacy, and enhancing malware detection through advanced machine learning approaches. His research shows a clear evolution from traditional network security problems to more complex challenges in modern distributed AI systems.

Dr. Li has successfully mentored numerous graduate students who have become active contributors in the field, including Agnideven Palanisamy Sundar, Tianchong Gao, Qin Hu, and Ryan Hosler, who frequently appear as co-authors on his publications. His research has been supported by various funding mechanisms that have enabled his team to tackle significant challenges in network security and privacy.

His laboratory focuses on practical implementations of security and privacy solutions, with particular emphasis on real-world applicability of theoretical concepts. Current research directions include enhancing the security of federated learning systems, developing more robust privacy-preserving techniques for social networks, and creating advanced malware detection systems using deep learning approaches.