Kumamoto Welcomes AIVR 2022

Keynote Speakers

Prof. Xiang-Gen Xia
Fellow of IEEE

University of Delaware, USA

Biography: Xiang-Gen Xia received his B.S. degree in mathematics from Nanjing Normal University, Nanjing, China, and his M.S. degree in mathematics from Nankai University, Tianjin, China, and his Ph.D. degree in electrical engineering from the University of Southern California, Los Angeles, in 1983, 1986, and 1992, respectively. He is currently the Charles Black Evans Professor, Department of Electrical and Computer Engineering, University of Delaware, Newark, Delaware, USA. Dr. Xia was the Kumar’s Chair Professor Group Professor (guest) in Wireless Communications, Tsinghua University, during 2009-2011, the Chang Jiang Chair Professor (visiting), Xidian University, during 2010-2012, and the WCU Chair Professor (visiting), Chonbuk National University, during 2009-2013. Dr. Xia’s current research interests include space-time coding, MIMO and OFDM systems, digital signal processing, and SAR and ISAR imaging. He is the author of the book Modulated Coding for Intersymbol Interference Channels (New York, Marcel Dekker, 2000). Dr. Xia received the National Science Foundation (NSF) Faculty Early Career Development (CAREER) Program Award in 1997, the Office of Naval Research (ONR) Young Investigator Award in 1998, and the Outstanding Overseas Young Investigator Award from the National Nature Science Foundation of China in 2001. He is currently serving and has served as an Associate Editor for numerous international journals including IEEE Transactions on Signal Processing, IEEE Transactions on Wireless Communications, IEEE Transactions on Mobile Computing, IEEE Transactions on Vehicular Technology, and Science China -- Information Sciences. Dr. Xia is Technical Program Chair of the Signal Processing Symp., Globecom 2007 in Washington D.C. and the General Co-Chair of ICASSP 2005 in Philadelphia. He is a Fellow of IEEE.

Prof. Shrikanth (Shri) Narayanan
Fellow of NAI, ASA, IEEE, ISCA, APS, AAAS, and AIMBE

University of Southern California, USA

Biography:  Shrikanth (Shri) Narayanan is University Professor and Niki & C. L. Max Nikias Chair in Engineering at the University of Southern California, where he is Professor of Electrical & Computer Engineering, Computer Science, Linguistics, Psychology, Neuroscience, Pediatrics, and Otolaryngology—Head & Neck Surgery, Director of the Ming Hsieh Institute and Research Director of the Information Sciences Institute. Prior to USC he was with AT&T Bell Labs and AT&T Research. His research focuses on human-centered information processing and communication technologies. He is a Guggenheim Fellow and a Fellow of the National Academy of Inventors, the Acoustical Society of America, IEEE, ISCA, the American Association for the Advancement of Science (AAAS), the Association for Psychological Science, and the American Institute for Medical and Biological Engineering (AIMBE). He is a recipient of several honors including the 2015 Engineers Council’s Distinguished Educator Award, a Mellon award for mentoring excellence, the 2005 and 2009 Best Journal Paper awards from the IEEE Signal Processing Society and serving as its Distinguished Lecturer for 2010-11, a 2018 ISCA CSL Best Journal Paper award, and serving as an ISCA Distinguished Lecturer for 2015-16, Willard R. Zemlin Memorial Lecturer for ASHA in 2017, and the Ten Year Technical Impact Award in 2014 and the Sustained Accomplishment Award in 2020 from ACM ICMI. He has published over 900 papers and has been granted eighteen U.S. patents. His research and inventions have led to technology commercialization including through startups he co-founded: Behavioral Signals Technologies focused on the telecommunication services and AI based conversational assistance industry and Lyssn focused on mental health care delivery, treatment and quality assurance. He serves as the inaugural Vice President–Education for the IEEE Signal Processing Society.

Title: Toward Trustworthy Human-centered Behavioral Machine Intelligence

Abstract: Converging technological advances in sensing, machine learning and computing offer tremendous opportunities for continuous contextually rich yet unobtrusive multimodal, spatiotemporal characterization of an individual’s behavior and state, and of the environment within which they operate. This in turn is enabling novel possibilities for understanding and supporting various aspects of human-centered applications notably in psychological health and well-being. This talk will highlight some of the advances, opportunities and challenges in gathering human-focused data and creating algorithms for machine processing of such cues. It will report efforts in Behavioral Signal Processing (BSP)—technology and algorithms for quantitatively and objectively understanding typical, atypical and distressed human behavior—with a specific focus on communicative, affective and social behavior. Examples will be drawn from health and wellbeing realms such as Autism Spectrum Disorder, Couple therapy, Depression, Suicidality, and work place behavior. It will also discuss the challenges and opportunities in creating trustworthy signal processing and machine learning approaches that are inclusive, equitable, robust, safe and secure e.g., with respect to protected variables such as gender/race/age/ability etc.

Prof. Chip Hong Chang
Fellow of IEEE and IET

Nanyang Technological University, Singapore

Biography: Chip Hong Chang is an Associate Professor at the Nanyang Technological University (NTU) of Singapore. He held concurrent appointments at NTU as Assistant Chair of Alumni of the School of EEE from 2008 to 2014, Deputy Director of the Center for High Performance Embedded Systems from 2000 to 2011, and Program Director of the Center for Integrated Circuits and Systems from 2003 to 2009. He has coedited five books, and have published 13 book chapters, more than 100 international journal papers (>80 are in IEEE), more than 180 refereed international conference papers (mostly IEEE), and have delivered over 50 keynotes, tutorial and invited seminars. His current research interests include hardware security, trustworthy sensing, anti-spoofing biometric, secure edge AI and PQC accelerators. Dr. Chang currently serves as the Senior Area Editor of IEEE Transactions on Information Forensic and Security (TIFS), and Associate Editor of the IEEE Transactions on Circuits and Systems-I (TCAS-I) and IEEE Transactions on Very Large Scale Integration (TVLSI) Systems. He was the Associate Editor of the IEEE TIFS and IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), IEEE Access, IEEE TCAS-I, etc.. He also guest edited about 10 journal special issues. He has held key appointments in the organizing and technical program committees of more than 60 international conferences (mostly IEEE). He is the 2018-2019 IEEE CASS Distinguished Lecturer, a Fellow of the IEEE, IET and AAIA. He was recently conferred the Award of Excellence in Hardware Security by the Venus International Foundation Center for Advance Research and Design.

Title: Data Augmentation Based Backdoor for Poisoning and Watermarking of Deep Neural Networks

Abstract:  The decision boundaries of lower bias complex deep neural network (DNN) are more easily overstrained by source distribution of the training dataset to perform poorly on domain shift. By increasing the size and diversity of the training dataset, data augmentation can reduce the variance of complex model to overcome the overfitting problem and increase its generalization capability. This talk will present two atypical and contrary uses of data augmentation on DNNs. While the global market capitalization of artificial intelligence (AI) product has risen tremendously in recent years, deployment of pre-trained DNN models continues to be threatened by the notorious backdoor attacks. The first part of this talk will demonstrate that a data augmentation based backdoor attack can achieve higher stealth, attack success rate, and robustness against state-of-the-art backdoor detectors. As the payoff of a well-trained proprietary DNN model is an outcome of heaving investment in computing power and labour on arduous data collection and labelling tasks, it deserves specific protection and digital rights management. Unfortunately, surrogate attacks and emerging model extraction techniques make it feasible to reverse engineer a deployed DNN model and rebuild an AI product or solution with similar quality at a lower cost than re-designing a DNN from scratch. The rampant DNN IP infringement is further exacerbated by the lack of buyer traceability to deter dishonest users from misappropriation of distributed models. The pirated model may undergo post-processing or transfer learning to fit into the attacker’s use cases to evade IP detection. To deal with this problem, a new backdoor based buyer-traceable watermarking scheme against model piracy and misappropriation will be presented in the second part of this talk.