[Keynote Speech I]: 11:00 ~ 11:30, February 21, 2023 (Tuesday)
Prof. Myung Jong Lee (City University of New York, USA)
Hardware Machine Learning-based Host Intrusion Detection System using Stochastic Computing
Abstract:
As the primary element of connected world, IoT promises to transform the way we work, live, and play. As many of these IoT devices are resource constrained in terms of processing, bandwidth and storage, equipping security and intelligence on these devices faces enormous technical challenges. The hacking of IoT devices and privacy fears have already grabbedpublic attention. If the issue of IoT security is not resolved in a timely manner, the envisioned connected world built on IoT, may be a story in the distant future. This talk first discusses the information technology evolution toward IoT in the view of entropy expansion with examples in communications. Future trends of IoT technologies will be explored in the core areas of IoT including security and machine learning. To boost the security of resource-constrained IoT, we introduce small form factor, low energy consumed, hardware based HIDS (Host Intrusion Detection System). This innovative design is possible by exploiting the inherent property of Stochastic Computing (SC): a) reduced silicon space and energy consumption; b) operated in probabilistic domain. In SC, complex mathematical operations are implemented probabilistically using simple digital gates. Thus, Deep Neural Network (DNN) can run in hardware with minimal usage of silicon space using SC. Major challenges in designing DNN using SC domain such as activation function and SoftMax beget new SC hardware modules theoretically more accurate for NNA. AHIDS system based on SC is implemented using FPGA and a Demo system will be presented. At the end, a short introduction of Dr. Lee’s current research efforts including NSF COSMOS Testbed and a transpacific high speed testbed between CUNY and Kyutech Japan. Q & A followed.
Biography
Dr. Myung Jong Lee received a B.S and an MS from Seoul National University in Korea and Ph.D degree from Columbia University in electrical/electronics engineering. He is currently a professor at the Dept of Electrical & Computer Engineering City University of New York. He is also an adjunct professor at GIST. He was a visiting professor to Bellcore, Seoul National University, and Samsung Advanced Institute of Technology. Dr. Lee’s recent research interests include Machine learning approaches for 6G, edge and mobile cloud computing, secure V2X, and stochastic computing applications. Currently, Dr. Lee leads CUNY site for NSF PAWR COSMOS testbeds, a city scale future wireless programmable testbed in Manhattan and the COSM-IC for Inter-continent high speed fiber network. In particular, he is leading a Transpacific Testbed between CCNY and Kyutech Japan via COSMIC testbed. His researches have been funded by government agencies and leading industries, including, NSF, ARL, Samsung, ETRI, and NICT. He authored and co-authored over 200 international journal & conference papers, a book, book chapters, more than 25 U.S and international patents. Dr. Lee also actively contributes to international standard organizations IEEE and ZigBee (TG chairs for IEEE 802 15.5 &15.8). Dr. Lee’s research group developed the first NS-2 simulator for IEEE 802.15.4, a standard NS-2 distribution widely used for wireless sensor network researches. He received the best paper awards (IEEE CCNC 2005, INCos2019, EAI 2016) and CUNY Performance Excellence Award.
[Keynote Speech II]: 11:30 ~ 12:00, February 21, 2023 (Tuesday)
Prof. Yan Zhang (University of Oslo, Norway)
Machine Learning in Digital Twin Edge Networks
Abstract:
In this talk, we mainly introduce our proposed new research direction: Digital Twin Edge Networks (DITEN). We first present the concept and model related to Digital Twin (DT) and DITEN. Then,we focus on new research challenges and results when machine learning is exploited in DITEN, including federated learing, deep reinforcement learning and transfer learning. Edge association and DT mobility, as unique research questions, will be defined and analyzed. We are also expecting that the talk will help the audience understand the future development of edge computing, e.g., digital twin edge networks in the context of Metaverse.
Biography
Yan Zhang is currently a Full Professor with the Department of Informatics, University of Oslo, Norway. His research interests include next-generation wireless networks leading to 6G, green and secure cyber-physical systems. Dr. Zhang is an Editor for several IEEE transactions/magazine. He is a program/symposium chair in a number of conferences, including IEEE IWQoS 2022, IEEE ICC 2021, IEEE SmartGridComm 2021. He is the Chair of IEEE Communications Society Technical Committee on Green Communications and Computing (TCGCC). He is an IEEE Communications Society Distinguished Lecturer and IEEE Vehicular Technology Society Distinguished Speaker. He was an IEEE Vehicular Technology Society Distinguished Lecturer during 2016-2020. Since 2018, Prof. Zhang was a recipient of the global “Highly Cited Researcher” Award (Web of Science top 1% most cited worldwide). He is Fellow of IEEE, Fellow ofIET, elected member of Academia Europaea (MAE), elected member of the Royal Norwegian Society of Sciences and Letters (DKNVS), and elected member of Norwegian Academy of Technological Sciences (NTVA).