Reinforcement Learning Aided Privacy Protection for IoT
Internet of things (IoTs) have to protect user privacy against inference attacks for location-based services and healthcare applications. The optimal IoTs privacy protection policy that makes a trade-off between privacy and data utility usually depends on the knowledge of the network model and the attack pattern. In this talk, we present IoT reinforcement learning based privacy protection schemes that enable IoT devices to optimize the privacy protection policy without being aware of the inference attack model in dynamic IoTs. We also present a deep learning version that compresses the state space and handles the high-dimensional continuous privacy protection policy space to further accelerate the learning speed and improve both the privacy protection level and the quality of services.
Date and Time
Location
Hosts
Registration
Add Event to Calendar
Speakers
Biography:
Liang Xiao is currently a Professor in the Department of Communication Enginnering, Xiamen University, Fujian, China. She is an IEEE Senior member, and member of IEEE Technical Committee on Big Data. She has served in several editorial roles, including an associate editor of IEEE Trans. Information Forensics & Security and IEEE Trans. Commun. Her research interests include wireless security, machine learning, and wireless communications. She won the best paper award for 2017 IEEE ICC and 2016 IEEE INFOCOM Bigsecurity WS. She received the B.S. degree in communication engineering from Nanjing University of Posts and Telecommunications, China, in 2000, the M.S. degree in electrical engineering from Tsinghua University, China, in 2003, and the Ph.D. degree in electrical engineering from Rutgers University, NJ, in 2009. She was a visiting professor with Princeton University, Virginia Tech, and University of Maryland, College Park.
Address:Canada