Title: Adversarial Machine Learning: an introduction and tutorial
Abstract: Deep learning has become increasingly popular in the past few years. This is largely attributed to a family of powerful models called deep neural networks (DNNs). With many stacked layers, and millions of neurons, DNNs are capable of learning complex non-linear mappings, and have demonstrated near or even surpassing human-level performance in a wide range of applications such as image classification, object detection, natural language processing, speech recognition self-driving cars, playing games or medical diagnosis. Despite their great success, DNNs have recently been found vulnerable to adversarial examples (or attacks), which are input instances slightly modified in a way that is intended to fool the model. Such a surprising weakness of DNNs has raised security and reliability concerns on the development of deep learning systems in safety-critical scenarios such as face recognition, autonomous driving, and medical diagnosis. Since the first discovery, this has attracted a huge volume of work on either attacking or defending DNNs against these attacks. In this tutorial, we will introduce this adversarial phenomenon, explanations to this phenomenon, and techniques that have been developed for both attack and defense.
Biography: Xingjun Ma is an outstanding alumnus of Jilin University. He obtained his Bachelor’s Degree from College of Software of Jilin University in 2010, Master’s Degree from College of Software of Tsinghua University in 2015, and Doctoral Degree from Department of Computer of University of Melbourne, Australia in 2019. He is an Assistant Lecturer at the University of Melbourne since 2019. He engaged in Machine Learning, Deep Learning related research, focusing on the security issues in Deep Learning: Adversarial Machine Learning. He successively published more than 10 papers in top conferences ICML/ICLR/CVPR/ICCV/AAAI/IJCAI, many of which have been selected as Oral papers, such as ICLR2018, ICML2018/2019, etc.
Personal page: http://xingjunma.com/.
Time: 13: 30pm, Tuesday, December 24, 2019
Venue: School of Artificial Intelligence (Room 601, Administration Building, Central Campus)
Organizer: School of Artificial Intelligence, Jilin University
