Keynote

My T. Thai, PhD

University of Florida, USA

Research Foundation Professor

Associate Director of UF Nelms Institute for the Connected World

Fellow of IEEE

Title: Federated Learning: A False Sense of Security?

Abstract:

Federated Learning (FL) has emerged as a promising large-scale collaborative learning framework for its potential to protect user privacy and security. However, this promise has been constantly challenged. In this talk, we show that FL in its primitive form offers little to no privacy and security protection, by analyzing several attack vectors, both from malicious users to a dishonest server. Even with a layer of protection from differential privacy and secure aggregation, we further demonstrate that current FL implementation provides no guarantee on privacy and security, thus calling for a fundamental re-design.

Short-Bio: My T. Thai is a University of Florida (UF) Research Foundation Professor, Associate Director of UF Nelms Institute for the Connected World, and a fellow of IEEE. Dr. Thai's current research interests include Trustworthy AI, Quantum Computing, and Optimization. The results of her work have led to 7 books and 300+ publications in highly ranked international journals and conferences, including several best paper awards from the IEEE and ACM. Dr. Thai received many recognitions, including UF Research Foundation professorship, IoT Term Endowed professorship, NSF CAREER Award, and DTRA Young Investigator Award. Among many professional activities, Dr. Thai currently serves as Editor-in-Chief of the Journal of Combinatorial Optimization, EiC of the IET Blockchain journal, and book series editor of Springer Optimization and Its Applications.

Latifur Khan, PhD

University of Texas at Dallas, USA

Computer Science Professor

Fellow of IEEE, IET, BCS

Title: Semi-Supervised Learning, and Life Long Learning for Social Good, Cyber-Security and Blockchain Areas

Abstract:

In this presentation, I will focus on Semi-supervised learning, lifelong learning and their applications. With regard to semi-supervised learning, various efforts have been proposed for reducing the annotation cost when training Deep neural networks (DNN). Semi-Supervised Learning (SSL) is one of the solutions that has been provably handy in leveraging unlabeled instances to mitigate the efficacy of the DNN model’s performance and has been attracting an increasing amount of attention in recent times. In this work, our main insight is that semi-supervised learning can benefit from recently proposed unsupervised contrastive learning approach, which aims to achieve the positive concentrated and negative separated representation in the unlabeled feature space. Herein, we introduce MultiCon, a semi-supervised learning paradigm that aims at learning data augmentation invariant based embedding. Experiments on multiple standard datasets including Covid19 Chest X-ray images, and CT Scans demonstrate that MultiCon achieves state-of-the-art performance across existing SSL benchmarks. In addition, we will demonstrate how semi-supervised learning can be used to and identify Choroidal Tumors in Fundus Photographs. In addition, by utilizing semi-supervised learning, we will find vulnerable functions in application libraries, and in the smart contract of blockchain area.

Short-Bio: Dr. Latifur Khan is currently a full Professor (tenured) in the Computer Science department at the University of Texas at Dallas, USA where he has been teaching and conducting research since September 2000. He received his Ph.D. degree in Computer Science from the University of Southern California (USC) in August of 2000. In addition, he received his bachelor degree in Computer Science and Engineering (CSE) from Bangladesh University of Engineering and Technology (BUET) with first class honors (2nd position).

Dr. Khan is a fellow of IEEE, IET, BCS, and an ACM Distinguished Scientist. He has received prestigious awards including the IEEE Technical Achievement Award for Intelligence and Security Informatics, IEEE Big Data Security Award, and IBM Faculty Award (research) 2016. Dr. Khan has published over 300 papers in premier journals and prestigious conferences. Currently, Dr. Khan’s research focuses on big data management and analytics, data mining and its application to cyber security, and complex data management including geospatial data and multimedia data. His research has been supported by grants from NSF, NIH, the Air Force Office of Scientific Research (AFOSR), DOE, NSA, IBM, and HPE. More details can be found at www.utdallas.edu/~lkhan.