Frontiers in Fake Media Generation and Detection

The book presents recent advances in the generation and detection of fake multimedia. It also presents some frontiers in defensive techniques in front of skillfully cloned media. The ultimate purpose of the research direction presented by this book is to build up a trustworthy media network benefited by an iron dome in front of media clones' attacks. The book focusses on (1) applications of deep generative models in the generation of fake multimedia, and (2) cyber-defensive and detective techniques in front of cyberattacks. The book is composed of three parts: (i) introduction, (ii) fake media generation, and (iii) fake media detection.

Presents recent advances in the generation and detection of fake multimedia Focusses on applications of deep generative models in the generation of fake multimedia Serves as a reference resource for graduates, researchers and lecturers in forensic science, artificial intelligence, and machine learning

Auteur

Mahdi Khosravy was born in Birjand, Iran, 1979. He received BSc. in Electrical Engineering (bio-electric) from the Sahand University of Technology, Tabriz, Iran, and MSc. in Biomedical Engineering (bio-electric) from Beheshti University of Medical Studies, Tehran, Iran. Mahdi received his Ph.D. in Interdisciplinary Intelligent Systems from University of the Ryukyus, Okinawa, Japan. He was awarded by the head of the University for excellence in research activities. To grow his international experience in education and research, in September 2010, he joined the University of Information Science and Technology, North Macedonia. In July 2017, he became an associate professor. August 2018 he joined the Energy lab in the University of the Ryukyus, Japan as a Visiting Researcher, and from April 2018 to September 2019, he was jointly a visiting associate professor in the Electrical Engineering Department, Federal University of Juiz de Fora in Brazil. From 2019 to 2021, he was a specially appointed researcher in Osaka University under the MediaClone project. Currently, he is a senior research scientist in Cross Labs, Cross-compass Ltd. Tokyo, Japan. He is a member of IEEE.

Isao Echizen received B.S., M.S., and D.E. degrees from the Tokyo Institute of Technology, Japan, in 1995, 1997, and 2003, respectively. He joined Hitachi, Ltd. in 1997 and until 2007 was a research engineer in the company's systems development laboratory. He is currently a director and a professor of the Information and Society Research Division, the National Institute of Informatics (NII), a director of the Global Research Center for Synthetic Media, the NII, and a professor in the Department of Information and Communication Engineering, Graduate School of Information Science and Technology, The University of Tokyo, Japan. He was a visiting professor at Tsuda University, Japan, at the University of Freiburg, Germany, and at the University of Halle-Wittenberg, Germany. He is currently engaged in research on multimedia security and multimedia forensics. He currently serves as a research director in CREST FakeMedia project, Japan Science and Technology Agency (JST). He received the Best Paper Award from the IPSJ in 2005 and 2014, the Fujio Frontier Award and the Image Electronics Technology Award in 2010, the One of the Best Papers Award from the Information Security and Privacy Conference in 2011, the IPSJ Nagao Special Researcher Award in 2011, the DOCOMO Mobile Science Award in 2014, the Information Security Cultural Award in 2016, and the IEEE Workshop on Information Forensics and Security Best Paper Award in 2017. He was a member of the Information Forensics and Security Technical Committee and the IEEE Signal Processing Society. He is the Japanese representative on IFIP TC11 (Security and Privacy Protection in Information Processing Systems), a member-at-large of board-of-governors of APSIPA, and an editorial board member of the IEEE Transactions on Dependable and Secure Computing and the EURASIP Journal on Image and Video processing.

Noboru Babaguchi received the B.E., M.E. and Ph.D. degrees in communication engineering from Osaka University, in 1979, 1981 and 1984, respectively. He is currently a Professor of the Department of Information and Communications Technology, Osaka University. From 1996 to 1997, he was a Visiting Scholar at the University of California, San Diego. His research interests include image/video analysis, multimedia computing and intelligent systems. Recently, he has been engaged in privacy protection for visual information, and security and fabrication of multimedia. He has published over 250 journal and conference papers and several textbooks. Prof. Babaguchi received Best Paper Award of PCM2006 and IAS2009. He is on the editorial board of Multimedia Tools and Applications, and New Generation Computing. He served as a Guest Editor of IEEE TIFS, Special Issue onIntelligent Video Surveillance for Public Security & Personal Privacy He also served as a workshop Co-chair of MIR2001, a Track Co-chair of IEEEICME2006, a General Co-chair of MMM2008, a Sub-Track Chair of APSIPAASC 2009, a General Co-Chair of ACM Multimedia 2012, a Track Co-Chair of ICPR2012, an Area Chair of IEEE ICME2013, and an Honorary Co-Chair of ACM ICMR2018. He also served on program committee of international conferences in multimedia related fields. He is a Fellow of IEICE, a Senior Member of IEEE, and a member of ACM, IPSJ, ITE and JSAI.

Contenu
Part 1: Introduction.- Chapter 1. Deepfakes and Society: What lies ahead?.- Chapter 2. Adversarial Examples and Defenses.- Part 2: Fake Media Generation.- Chapter 3. Adversarial Attacks.- Chapter 4. Robust Deepfake On Unrestricted Media: Generation And Detection.- Chapter 5. Spoofing Tweet Generator considering Points of Interest of Target User.- Part 3: Fake Media Detection.- Chapter 6. Defense Against Adversarial Attacks.- Chapter 7. Adversarial Defense with Secret Key.- Chapter 8. A Practical Guide to Logical Access Voice Presentation Attack Detection.- Chapter 9. Cross-Domain Fake News Detection on Social Media: A Context-Aware Adversarial Approach.- Part 4: Further Topics and Trends.- Chapter 10. Recognizer Cloning Attack on Image Recognition Services and Its Defending Method.- Chapter 11. Dynamic deception using social media.