Speech abstract: In this talk, the concept of perceptual hashing and its differences with cryptographic hash function and semantic retrieval hashing are first given. Secondly, we illustrate some typical application scenarios of perceptual hashing in the field of image content authentication. Thirdly, a series of representative methods for perceptual image hashing and some of our works are introduced. Finally, the summary and further research directions are discussed.

Bio: Dr. Qin is currently a Professor at the School of Optical-Electrical and Computer Engineering with University of Shanghai for Science and Technology, China. His research interests include multimedia intelligent computing, AI security, data hiding and image processing in encrypted domain. He has authored or coauthored more than 200 articles in these research areas. He was selected as the Highly Cited Chinese Researchers by Elsevier in 2020 and the World’s Top 2% Scientists in 2019-2022. 

Speech abstract:  This talk explores generative agents in AI networks, covering their applications, methods, challenges, and future outlook. These agents, powered by large language models like GPT and adversarial learning techniques and reinforcement learning, are crucial for tasks like synthetic data generation and network optimization. Despite their benefits, concerns regarding privacy and AI ethics persist. Distributed privacy-enhancing technologies offer hope for maximizing the potential of generative agents in building resilient and intelligent AI networks in the age of ChatGPT.

Bio: Dr. Tan is currently with Nanyang Technological University, Singapore. His research interests are networks, distributed optimization, Generative Artificial Intelligence (AI) and AI for Health-Tech. He serves or has served as an IEEE Distinguished Lecturer, an Editor for the IEEE Transactions on Cognitive Communications and Networking, IEEE/ACM Transactions on Networking and the IEEE Transactions on Communications.

Speech abstract: In the field of machine learning, it is often assumed that the number of samples in each class is roughly equal. However, in real-world scenarios, the data generated from enterprises or industries often exhibit imbalanced distributions. This imbalance poses significant challenges because traditional learning algorithms tend to favor the majority class while potentially overlooking the minority class. From a data mining perspective, minority classes often carry valuable knowledge, making them crucial. This report aims to explore the issues and theoretical research surrounding imbalanced learning. First, we present our recent studies on imbalanced learning, primarily focusing on addressing high-dimensional imbalanced problems through a multi-view perspective. We propose a multi-view optimization approach that enhances the classification performance of high-dimensional imbalanced data by generating and selecting optimized subviews and employing resampling techniques. Following this, we introduce an adaptive weighted broad learning system (AWBLS) and an incremental weighted ensemble broad learning system (IWEB). These systems effectively address outliers and noise in imbalanced data through sample weighting and density-based weighting mechanisms. Finally, we outline our future research directions, which aim to integrate broad learning systems, ensemble learning, and deep learning to address various scenarios in imbalanced learning.

Bio:  Dr. Yu is currently a Professor with the School of Computer Science and Engineering, South China University of Technology, Guangzhou, China. He is a distinguishable member of CCF (China Computer Federation), a senior member of IEEE and ACM, and the vice chair of ACM Guangzhou chapter. He is an associate editor of IEEE Transactions on Systems, Man, and Cybernetics: Systems. The research areas of Dr. Yu focus on artificial intelligence, data mining, machine learning and pattern recognition. He has authored or coauthored more than 170 refereed journal articles and international conference papers, including more than 60 articles in the journals of IEEE Transactions. 

Speech abstract: To be updated

Bio: Dr. Zhao currently works as a professor with the School of Electrical Engineering, Southwest Jiaotong University, Chengdu, China. His current research interests include adaptive filtering algorithm, adaptive network, information theoretical learning, and nonlinear system identification. At present, he is the author or coauthor of more than 140 international journal papers (SCI indexed), and the owner of 70 invention patents. He has served as an active reviewer for several IEEE Transactions, IET series, Signal Processing, and other international journals. And he was a handling editor of Signal Processing.