A Tutorial about Adversarial Attacks & Defenses in KDD 2021:

Deep neural networks (DNNs) have achieved unprecedented accomplishments in various machine learning tasks. However, recent studies demonstrate that DNNs are extremely vulnerable to adversarial examples. They are manually synthesized input samples which look benign but can severely fool the prediction of DNN models. For machine learning practitioners who are applying DNNs, understanding the behavior of adversarial examples will not only help them improve the safety of their models, but also can help them have deeper insights into the working mechanism of the DNNs. In this tutorial, we provide a comprehensive overview on the recent advances of adversarial examples and their countermeasures, from both practical and theoretical perspectives. From the practical aspect, we give a detailed introduction of the popular algorithms to generate adversarial examples under different adversary’s goals. We also discuss how the defending strategies are developed to resist these attacks, and how new attacks come out to break these defenses. From the theoretical aspect, we discuss a series of intrinsic behaviors of robust DNNs which are different from traditional DNNs, especially about their optimization and generalization properties. Finally, we introduce DeepRobust, a Pytorch adversarial learning library which aims to build a comprehensive and easy-to-use platform to foster this research field. Via our tutorial, the audience can grip the main ideas of adversarial attacks and defenses and gain a deep insight of DNN’s robustness.

Link to KDD21 official Website: https://kdd.org/kdd2021/

Tutorial Date/Time: Aug 15, 12am-3am (in SGT) or Aug 14, 12pm-3pm (in EST).

Tutorial Slides:

Presenters:

Han Xu is a Ph.D. student of Computer Science and Engineering at Michigan State University. Before joining MSU, he gained his master’s degree of Applied Statistics in the University of Michigan. His current research interest lies on adversarial attacks and defenses, with their applications on various deep learning tasks. He is one of the main contributors of the PyTorch library about adversarial learning, DeepRobust, which helps researchers who are interested in the field of adversarial learning. He also has several publications on adversarial attack and defense to top data mining conferences and journals such as SDM, and KDD Explorations. Yaxin Li.

Yaxin Li is a Ph.D. student of Computer Science and Engineering at Michigan State University. Her research interests mainly focus on adversarial robustness. She is the leader and one of the main contributors of DeepRobust, which is a Pytorch library to help researchers in this field and has already gained lots of attention in the community. She has several publications on adversarial attack and defense to top conferences including AAAI, SDM and KDD.

Xiaorui Liu. Xiaorui Liu is a PhD student in the Department of Computer Science and Engineering at MSU. His research mainly focuses on distributed optimization, robust machine learning, and machine learning on graphs. He has published high-quality papers in top-tier conferences such as ICLR, KDD, AISTATS, SDM, WSDM and ICHI.

Wentao Wang. Wentao Wang is a Ph.D. student in the computer science and engineering department at Michigan State University. His research interests mainly lie in building effective and robust machine learning models from various kinds of real-world scenarios. Before that, He received his bachelor’s degree in Computer Science and Technology from Sichuan University in China. He has published high-quality papers in top-tier conferences and journals such as EMNLP, ICDM, SDM and TKDE.

Jiliang Tang. Jiliang Tang is an assistant professor in the computer science and engineering department at Michigan State University since Fall@2016. Before that, he was a research scientist at Yahoo Research. He got his Ph.D. from Arizona State University in 2015 and his MS and BE from Beijing Institute of Technology in 2010 and 2008, respectively. His research interests include data mining, machine learning and their applications in social media and education. He was the recipient of 2020 SIGKDD Rising Star Award, 2020 Distinguished Withrow Research Award, 2019 NSF Career Award, 2019 IJCAI Early Career Talk Award, and 7 best paper awards (or runner-ups) including WSDM2018 and KDD2016. His dissertation won the 2015 KDD Best Dissertation runner up and Dean's Dissertation Award. He serves as top data science conference organizers (e.g., KDD, SIGIR, WSDM, and SDM) and journal editors (e.g., TKDD and ACM Books). He has published his research in highly ranked journals and top conference proceedings, which received more than 14,400 citations with h-index 60 and extensive media coverage.

External Links:

Data Science and Engineering Lab (DSE) at Michigan State University: http://dse.cse.msu.edu/.

DeepRobust (a Pytorch Platform for Adversarial Learning in Image & Graph data): https://github.com/DSE-MSU/DeepRobust/