Machine Learning and Cybersecurity: A Tale of Two Buzzwords

ABSTRACT

Recent advances in machine learning, especially generative AI, have made significant impacts on a wide range of research disciplines including security and privacy. Meanwhile, a broad spectrum of cyber-attacks against machine learning systems has been proposed. Such attacks aim to break the integrity or confidentiality of the models. In this talk, I will discuss the synergy between cybersecurity and AI/ML, and introduce several research projects from KU’s InfoSec group on adversarial/trustworthy machine learning. Through this talk, we hope to highlight the security and privacy issues in AI/ML systems, which may be helpful for the audience to identify the opportunities and challenges in their own research fields.

BIOGRAPHY

Bo Luo is a professor in the EECS department at the University of Kansas. He is the director of the Center for High Assurance and Secure Systems (HASS) at KU's Institute of Information Sciences (I2S). He received a Ph.D. degree from Pennsylvania State University in 2008, an M.Phil degree from the Chinese University of Hong Kong in 2003, and a B.E. from the University of Sciences and Technology of China in 2001. His recent works mostly lie in the intersection of AI/ML and privacy and security. Dr. Luo has actively published in top conferences and journals such as IEEE S&P, ACM CCS, USENIX Security, NDSS, ACM Multimedia, IEEE TKDE, IEEE TIFS, IEEE TDSC, etc. He received the KU EECS Excellence in Undergraduate Teaching Professorship in 2023, the Miller Scholar Award of the University of Kansas in 2016, 2017, and 2021, and the Miller Professional Development Award in 2015. He is also the recipient of ACSAC 2017, ACSAC 2021, ACM/IEEE ICPC 2024 Best Paper awards, and CCS 2022 Best Paper honorable mention.