Trustworthy Machine Learning:  Security, Privacy, and Fairness

浙江大学网络空间安全学院

学术报告

  摘 要  

With continued advances in science and technology, digital data have grown at an astonishing rate in various domains and forms, such as business, geography, health, multimedia, network, text, and web data. Machine learning, a powerful tool for automatically extracting, managing, inferencing, and transferring knowledge, has been proven to be extremely useful in understanding the intrinsic nature of real-world big data. Despite achieving remarkable performance, machine learning models, especially deep learning models, suffer from severe security and privacy threats caused by malicious users, hackers, and spies or undermine fairness by inadvertently discriminating against specific demographic groups. There is an immediate and crucial need for theoretical and practical techniques to identify the vulnerability of machine learning models and explore the defense mechanism to ensure they are trustworthy.

In this talk, I will introduce problems, challenges, and solutions for characterizing and understanding vulnerability, privacy risks, and unfairness of machine learning models in the real world. I will also describe my recent research on security, privacy, and fairness problems in machine learning. I will conclude the talk by sketching interesting future directions for trustworthy machine learning.

  报告人简介  

Yang Zhou is an Assistant Professor in the Department of Computer Science and Software Engineering at the Auburn University. Prior to that, he received his Ph.D. degree in the College of Computing at the Georgia Institute of Technology. His current research interests lie in the areas of Trustworthy Machine Learning, Parallel, Distributed, and Federated Learning, Graph Machine Learning, and Natural Language Processing. He has published more than 80 research papers in top venues of machine learning (ICML, NeurIPS), data mining (KDD, ICDM, TKDD, DMKD, KAIS), artificial intelligence (AAAI, IJCAI, TIST), natural language processing (ACL, EMNLP), Web (WWW, TWEB), high performance computing (HPDC, SC), database systems (VLDB, ICDE, TKDE, VLDBJ), networking (JSAC, TOIT), web services (ICWS, TSC), and software engineering (ISSTA). The developed models and frameworks have been widely used by many research groups and six papers have been included in reading lists and taught in courses at universities worldwide. He was named as KDD Rising Star by Microsoft Academic Search and Microsoft Research Asia in 2016. The lab has built close collaborative relationships with Amazon, IBM, Microsoft, Sony, Baidu, and JD Research.