Cyber Vaccine for Deepfake Immunity
Dr. Ching-Chun Chang
National Institute of Informatics, Tokyo, Japan
Abstract:
Deepfakes pose an evolving cybersecurity threat that calls for the development of automated countermeasures.
While considerable forensic research has been devoted to the detection and localisation of deepfakes, solutions for ‘fake-to-real’ reversal are yet to be developed. In this study, we introduce the concept of cyber vaccination for conferring immunity to deepfakes. In other words, we aim to impart a self-healing ability to the face-containing media so that the original content can be recovered after manipulation by AI-based deepfake technology. Analogous to biological vaccination which uses injected antigens to induce immunity prior to infection by an actual pathogen, cyber vaccination simulates deepfakes and performs adversarial training to build a defensive immune system. Aiming to build up attack-agnostic immunity with limited computational resources, we propose simulating various deepfakes with one single overpowering attack: face masking. The proposed immune system consists of a vaccinator for inducing immunity and a neutraliser for recovering facial content. Experimental evaluations demonstrate effective immunity to face replacement and various types of corruption.
Biography:
Ching-Chun Chang received his PhD in Computer Science from the University of Warwick, UK, in 2019. He participated in a short-term scientific mission supported by European Coop- eration in Science and Technology Actions at the Faculty of Computer Science, Otto-von-Guericke-Universität Magdeburg, Germany, in 2016. He was granted the Marie-Curie fellowship and participated in a research and innovation staff exchange scheme supported by Marie Skłodowska-Curie Actions at the Department of Electrical and Computer Engineering, New Jersey Institute of Technology, USA, in 2017. He was a Visiting Scholar with the School of Computer and Mathematics, Charles Sturt University, Australia, in 2018, and with the School of Information Technology, Deakin University, Australia, in 2019. He was a Research Fellow with the Department of Electronic Engineering, Tsinghua University, China, in 2020. He is currently a Postdoctoral Research Fellow with the National Institute of Informatics, Japan. His research interests include steganography, forensics, biometrics, cybersecurity, computer vision, computational linguistics and artificial intelligence.