IEEE International Conference on High Performance Switching and Routing
6–8 June 2022 // Virtual Conference

Invited Female Session

Title: Data Mining for Security of the Industrial Internet of Things

Acronym: DMS

Description of the special session topic:

The Industrial Internet of Things (IIoT) brings the cyber and the physical worlds together. It provides huge advantages to improve the efficiency of industrial production and introduces major security challenges because of the extensive networking between internal industrial networks and external information networks. Further, such IIoT security may trigger serious accidents to endanger public safety, especially in high-risk domains such as nuclear, aircraft, chemical, oil and mining, automatic driving, and transportation industry. In these domains, a small misoperation can be catastrophic. Industrial security tries to reduce such threats by defending the attacks from cyberspace. With the aid of various sensors and learning-based components in the industrial equipment, and the data mining algorithms, we can produce a feasible scheme to ensure the security of IIoT from the source by mining the features of the potential risks. Hence, there is a need to study and design data mining for security for the IIoT.


The invited speakers, including the title of the presentation, name, and bio:

1)  Liang Xiao

Title of the presentation: Learning Based Privacy Protection in Internet of Things

Abstract: The rapid development of the Internet of Things (IoT) has given birth to the emergence of service models such as intelligent transportation, telemedicine, and location-based services. However, they face different privacy issues, such as eavesdropping attack and advance persistent threat, which has caused huge economic losses and even harm national security. Additionally, these new service models face challenges such as the complexity of the IoT environment, the unknown privacy leakage model, the limited resources of the IoT devices, and the time-sensitive requirements. In this talk, we introduce the privacy protection schemes in three typical scenarios of cloud storage systems, mobile edge computing, and location-based services for privacy leakage in the IoT. We apply game theory, reinforcement learning, and differential privacy to investigate intelligent privacy protection scheme. This work provides a theoretical basis and useful suggestions for the future design of the IoT privacy protection framework.


Liang Xiao is currently a Professor in the Department of Informatics and Communication Engineering, Xiamen University, Fujian, China. As an IEEE Senior member, she has served in several editorial roles, including an associate editor of IEEE Transactions on Information Forensics & Security, IEEE Transactions on Communication and IEEE Transactions on Dependable and Secure Computing, and Guest Editor of IEEE Journal on Selected Topics in Signal Processing. Her research interests include wireless security, privacy protection, and wireless communications. She published two books and three book chapters. She won the best paper award for 2017 IEEE ICC, 2018 IEEE ICCS and 2016 IEEE INFOCOM Big security 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.


2) Yanwei Wu

Title of the presentation: Cybersecurity in Microgrid

Abstract: A microgrid is a small-scale distribution grid, made up of electricity users with local renewable and other energy sources. The smart microgrid can make intelligent decisions to produce significant savings by lowering energy costs and by managing onsite energy usage to avoid peak energy prices while supporting grid stability and improving return on investment. However, when utility companies extend their proprietary substation industrial network to the Internet to cover the grids, they face more critical cyber threats than other industries. Our project is to build a smart microgrid system on campus, develop cybersecurity technologies, and offer cybersecurity validation services to local companies.


Yanwei Wu is currently an Associate Professor in Computer Science and Software Engineering Department at University of Wisconsin, Platteville, Wisconsin, USA. She received her Ph.D. degree in Computer Science from Illinois Institute of Technology. She published in IEEE transactions and served as an editor, conference chair, member or reviewer in selected journals and conferences. Her research interests are cybersecurity. Her currently funded projects are “Risk Assessment in Pioneer Farm” and “Cybersecurity Testbed in Microgrid”.


3) Linlin Guo

Title of the presentation: A Research on Device-free Human Activity Recognition using Physical Layer Information

Abstract: Passive human activity recognition is a hot research topic with important theoretical value and broad application prospect in the field of wireless intelligent sensing. At present, there are many achievements in passive human activity recognition domain using wireless signals, such as activity detection, activity recognition, attribute estimation and trajectory tracking of people. Our research mainly explored the influence mechanism of human activity on WiFi signal changes by combining signal sensing theoretical model and deep learning algorithm. Through the exploration of signal propagation model, data representation, individual behavior habits and other aspects to gradually build the environment model, human model and activity model. The presentation will introduce our research on human behavior sensing in terms of human activity detection, human activity segmentation and human activity recognition. Our goals are to promote the human activity recognition in large-scale scene or the application of complex application environments, and provide theoretical model for further research and experience of enlightenment.


Linlin Guo is currently a lecturer in School of Information Science and Engineering at Shandong Normal University. She received the B.S. degree in Computer and Technology Department from Taishan University in 2011, the M.S. degree from Qufu Normal University in 2014, the Ph.D. degree from Dalian University of Technology in 2020. Her current research interests include Wireless sensing (device-free indoor localization and human activity recognition), wireless network, and machine learning. She has been actively publishing more than 10 papers in the high quality international journals and conferences.


4) Jia Liu

Title of the presentation: Variational Inference Assisted Ground Truth Analysis for Data Management of IIoT

Abstract: The continuous expanded scale of the industrial Internet of Things (IIoT) leads to IIoT equipments generating massive amounts of uncertain user data every moment. How to make use of these uncertain data in an efficient and safe way in the field of IIoT is still an open issue, such that it has attracted extensive attention from academia and industry. As a new machine learning paradigm, variational inference (VI) has great advantages in obtaining the ground truth from uncertain data. This article studies the VI technology applications to manage IIoT equipment data in wireless network environments. Therefore, we propose a VI algorithm assisted ground truth analysis for data management of IIoT (VIIIoT), which can take into account the privacy and efficiency of data training of IIoT equipment. VIIIoT provides more general insights into the forming of user features, can be easily extended to higher dimensions and has the merits of low complexity, easy scaling and generality. Experiments show that VIIIoT outperforms the other existing type of machine learning algorithms, and it has higher accuracy in terms of mean absolute error (MAE) and root mean square error (RMSE).


Jia Liu is currently a lecturer in the School of Cyber Security, Hangzhou Dianzi University, Hangzhou, China. She received the Ph.D. degree in software engineering from the Dalian University of Technology, Dalian, China, in 2021. From 2018 to 2019, she was a visiting PhD student in school of biomedical engineering from the University of California, Irvine, sponsored by China Scholarship Council. Her research interests include artificial intelligence, machine learning, variational inference, crowdsourcing, and computer vision. She published 11 papers in MONET, WCMC, Sensors, IECON etc.