[Seminar] Adversarial Learning: Foundations and Applications

Topic: Adversarial Learning: Foundations and Applications

Time: 15h00-16h30, Tuesday, April 25th, 2023

Speaker: Dr. Jingfeng Zhang, Research Scientist, RIKEN-AIP

✅  Location: Room 404, B1 Building, Hanoi University of Science and Technology

or online link on MS Teams: here

Abstract:

As machine learning (ML) models are reaching accuracy levels suitable for real-world applications, it is crucial to recognize that accuracy is not the only benchmark that matters. Developers must actively prepare ML models to be robust enough in the wild against any attempts to hack them. However, the ML models obtained by standard training (ST) cannot handle adversarial data that are algorithmically generated by adversarial attacks. An adversarial attack is an algorithm that applies specially designed tiny perturbations on natural data to transform them into adversarial data to mislead a trained model and let it give wrong predictions. Adversarial robustness aims to improve the robust accuracy of ML models on adversarial data, which can be achieved by adversarial training (AT). Specifically, AT has two purposes: (1) correctly classify the data (the same as ST) and (2) ensure no data fall nearby the decision boundaries (different from ST). Given that the test data may be adversarial, AT carefully simulates some adversarial attacks during training. Thus, the model has already seen many adversarial training data in the past with the purpose of generalizing to adversarial test data in the wild. 

This talk will introduce the three improvements of AT and two case studies on leveraging adversarial attack/training for evaluating/enhancing reliabilities of ML-powered methods. 

Speaker Bio:

Jingfeng Zhang is a researcher at the “Imperfect Information Learning Team’’ in RIKEN-AIP. Before RIKEN-AIP, he obtained his Ph.D. degree (in 2020) at the School of Computing at the National University of Singapore. He is the PI of multiple grants, including “JST Strategic Basic Research Programs, ACT-X, FY2021-2023”, “JSPS Grants-in-Aid for Scientific Research (KAKENHI), Early-Career Scientists, FY2022-2023”, “RIKEN-Kyushu Univ Science & Technology Hub Collaborative Research Program, FY2022”. 

He is a recipient of the RIKEN Ohbu Award 2021 (50 recipients each year in all RIKEN’s disciplines). He serves as an associate editor for IEEE Transactions on Artificial Intelligence. He is a long-standing reviewer for prestigious ML conferences such as ICLR, ICML, NeurIPS, etc. His long-term research interest is to build a secure and responsible ML environment. Check his homepage https://zjfheart.github.io for details.

Slides: to be updated…

Recording:  to be updated…