Recent Results on Object Detection and Data Augmentation
Prof. Jun-Wei Hsieh
National Yang-Ming Chiao-Tung University, Taiwan
Abstract:
AI comes quickly and urgently, and many companies are too late to react. Facing this increasingly international competitive environments, only combining research energies from academic and enterprises to jointly develop core AI technologies can overcome this difficulty. This talk will discuss how to realize the academic research energy into the industry, "fit" the AI technologies to local requirements, and then "commercialize" them to products. This talk will discuss recent results on object detection and data augmentation, also including their applications such as smart agriculture, smart transportation, smart healthcare, and smart drone.
Biography:
Jun-Wei Hsieh was an Associate Professor with the Department of Electrical Engineering, Yuan-Ze University, and a Visiting Researcher with the MIT AI Laboratory. Since August 2009, he had been a Professor and the Dean of the Department of Computer Engineering, National Taiwan Ocean University. After August 2019, he has been a Professor with the College of AI, National Yang-Ming Chiao-Tung University. He hosted or co-hosted a lot of large-scale AI projects from different companies and governments in the past. He has a lot of successful experiences in industrial-academic cooperation and technology transferring, especially in ITS. His research interests include AI, deep learning, smart farming, video surveillance, intelligent transportation systems, image and video processing, object recognition, machine learning, 3D printing, medical image analysis, and computer vision. In May 2019, he received the First Prize of the Ministry of Science and Technology Best Display Award and the Third Place of the AI Investment Potential Award. Due to his contributions in traffic flow estimation, he helped the Elan company receive the Gold Award from Taipei International Computer Show, in 2019. He also received the Outstanding Research Awards of National Taiwan Ocean University, in 2012, 2016, 2017, and 2019, the Outstanding Research Awards of Yuan Ze University, in 2006, 2007, 2008. He and his students received the Silver Medal of 2019 National College Software Creation Competition, the Silver Medal of 2018 National Microcomputer Competition, the Best Paper awards of Information Technology and Applications in Outlying Islands Conference, in 2013, 2014, 2016, 2017, 2018, and 2021, respectively, the Best Paper Award of Tanet 2017, the Best Paper Awards of NCWIA 2020, 2021, respectively, and the Best Paper Awards of IS3C 2020. He also received the Best Paper Award of CVGIP Conference, in 1999, 2003, 2005, 2007, 2014, 2017, and 2018, the Best Paper Award of DMS Conference, in 2011, the Best Paper Award of IIHMSP 2010, and the Best Patent Award of Institute of Industrial Technology Research, in 2009 and 2010, respectively. He also received the award of 2022 future technology in Taiwan.
Adversarial Machine Learning and Intrusion Detection Systems
Prof. Tarek Gaber
University of Salford, UK
Abstract:
The intrusion detection is an essential part of information security systems. Its purpose is to defend computer systems and networks against unauthorised access and harmful activities. In the past two decades, numerous machine learning (ML) algorithms have been strongly supported, and they have been shown to be effective. Nevertheless, ML is subject to a number of challenges. One of the most dangerous ones is the emergence of adversarial approaches to trick the classifiers. For building secure systems like, intrusion detection ones, it is essential to address this vulnerability in order to stop cybercriminals from using ML weaknesses as a backdoor to defeat IDS and cause damage to data and systems. In this talk, it is aimed to evaluate the robustness of ML/DL-based network intrusion detection system against several adversarial attacks. Then, we investigate several defence strategies against such attacks.
Biography:
Tarek Gaber is a Senior Lecturer at the University of Salford, UK, & an Associate Professor at Suez Canal University, Egypt. Dr. Gaber received his PhD in Computer Science from the University of Manchester in 2012. He has worked in many universities including the Faculty of Computers and Informatics, Suez Canal University, Faculty of Computers and Information Sciences, Ain Shams University, and the School of Computer Science, University of Manchester, Manchester, UK. He had a postdoctoral position at the Faculty of Electrical Engineering and Computer Science, VSB Technical University of Ostrava, Ostrava, Czech Republic. He is also a member of The Scientific Research Group in Egypt (SRGE). He has served as a co-chair and PC member in many international conferences and reviewed many scientific papers and participated in many scientific events (national/international conferences and workshops). He also served as Lead Guest Editor in man SCI international journals. He has more than 80 publications in international journals, conferences, and book chapters. In addition, he has 5 edited books. Tarek has successfully supervised many MSc-by-Research students and PhD students. He is currently supervising PhD and MSc students in information security and machine learning. His major research interests include cybersecurity, mobile authentication, machine learning, wireless sensor network, biometric authentication.
Reversible Data Hiding
Prof. Yao Zhao
Beijing Jiaotong University, China
Abstract:
Data hiding offers a way to embed data into cover medium for the purposes of ownership protection, authentication, fingerprinting, secret communication and annotation, etc. In most data hiding algorithms, the cover data is destroyed permanently and cannot be exactly restored after the embedded message is extracted. Recently, a new data hiding technique, namely, reversible data hiding (RDH), is proposed, in which both the cover data and the embedded message can be extracted from the marked content. This specific data hiding technique has been found to be useful in the military, medical and legal fields, where the recovery of the original content is required after data extraction.
In the talk, we will first introduce the concept, the basic principle and implementation of the RDH. Then we will survey the state-of-the-art. Finally, we will present some relative works in our lab.
Biography:
Yao Zhao received the B.S. degree from the Radio Engineering Department, Fuzhou University, Fuzhou, China, in 1989, and the M.E. degree from the Radio Engineering Department, Southeast University, Nanjing, China, in 1992, and the Ph.D. degree from the Institute of Information Science, Beijing Jiaotong University (BJTU), Beijing, China, in 1996.
He became an Associate Professor with BJTU in 1998 and became a Professor in 2001. From 2001 to 2002, he was a Senior Research Fellow with the Information and Communication Theory Group, Faculty of Information Technology and Systems, Delft University of Technology, Delft, The Netherlands. In 2015, he visited the Swiss Federal Institute of Technology, Lausanne, Switzerland (EPFL). From 2017 to 2018, he visited the University of Southern California. He is currently the Director of the Institute of Information Science, BJTU. His current research interests include image/video coding, digital watermarking and forensics, video analysis and understanding, and artificial intelligence.
Dr. Zhao serves on the Editorial Boards of several international journals, including as Associate Editors of the IEEE TRANSACTIONS ON CYBERNETICS, the IEEE TRSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, a Senior Associate Editor of the IEEE SIGNAL PROCESSING LETTERS, and an Area Editor of the Signal Processing: Image Communication. He was named as a Distinguished Young Scholar by the National Science Foundation of China in 2010, and was elected as a Chang Jiang Scholar of the Ministry of Education of China in 2013. He is fellows of the IET and the IEEE.