报告简介：We mainly focus on solving some identity authentication issues remaining in the IoT related application. Combined with blockchain, cryptographic protocols, dynamic Join-and-Exit mechanism and batch verification, a reliable and efficient security mechanism is proposed for smart IoT services. We also present our recent research results on machine learning applications in IoT security which is a crucial aspect for the cloud-based service in an IoT-enable environment. We will introduce our novel federated learning system which can both reduce the communication time by layer-based parameter selection and enhance the privacy protection by applying local differential privacy mechanism on the selected parameters.
个人简介：Chunhua Su received the B.S. degree for Beijing Electronic and Science Institute in 2003 and received his M.S. and PhD of computer science from Faculty of Engineering, Kyushu University in 2006 and 2009, respectively. He is currently working as a Professor in the Division of Computer Science, University of Aizu. He has worked as a postdoctoral fellow in Singapore Management University from 2009-2011 and a research scientist in the Cryptography & Security Department of the Institute for Infocomm Research, Singapore from 2011-2013. From 2013-2016, he has worked as an Assistant professor in School of Information Science, Japan Advanced Institute of Science and Technology. From 2016-2017, he worked a Professor in Graduate School of Engineering, Osaka University. His research interests include cryptanalysis, cryptographic protocols, privacy-preserving technologies in machine learning and IoT security & privacy. He has published more than 100 papers in international journals and conferences.