Trustworthy Video Analytics

Speaker: Dr. Yuan Hong , The Department of Computer Science and Cybersecurity Program Director at Illinois Institute of Technology (IIT)

Slides:csiro-0826-pets

Recording: https://webcast.csiro.au/#/videos/97e6ffa7-ed36-40f8-9f99-183a6435102b

Date and time: 26/8/21, 3-4 AEST

Title: Trustworthy Video Analytics

Abstract:  Massive amounts of videos are ubiquitously generated in personal devices and dedicated video recording facilities. A wide variety of video analytics tasks are frequently performed to extract knowledge from the videos for different purposes. In this talk, I will present the security vulnerabilities and privacy issues in video analytics, as well as the defense methods to mitigate such risks. First, we propose the first black-box attack framework that generates universal 3-dimensional (U3D) perturbations to subvert a variety of video deep neural networks (DNNs). The new attack is easy-to-launch, universal, transferable, and human-imperceptible. It can also bypass the state-of-the-art defense methods. Such an attack motivates the DNN-based video recognition systems to build and integrate more robust learning models. Second, we propose the first differentially private video analytics platform (VideoDP) which flexibly supports different video analyses with rigorous privacy guarantees. With this new paradigm of privacy for videos, adding or removing any sensitive visual element (e.g., human and object) does not significantly affect the analysis results. It supports general video analyses without compromising the privacy of individuals in the videos.

Bio:  Yuan Hong is an Assistant Professor of Computer Science and Cybersecurity Program Director at Illinois Institute of Technology. He received his Ph.D. degree from Rutgers University in 2014. His research interests primarily lie in the fields of security, privacy, optimization, and data science, such as differential privacy, secure multiparty computation, applied cryptography, adversarial learning, and certified robustness. He is a recipient of the NSF CAREER award, and his work has appeared in prestigious security and data science venues such as Oakland, CCS, PETS, AAMAS, CIKM, EDBT, ICDCS, TDSC, TIFS, TOPS and TKDE. His research is supported by numerous NSF and AFOSR awards.