IFS-L5: From Deepfake Detection to Template Inversion: Modern Media Forensics
Oral
Thu, 7 May, 16:30 - 18:30
Location: Room 133+134
Session Type: Oral
Track: Information Forensics and Security [IF]
Click the to view the manuscript on IEEE Xplore Open Preview
Thu, 7 May, 16:30 - 16:50

IFS-L5.1: LEVERAGING LARGE MULTIMODAL MODELS FOR AUDIO-VIDEO DEEPFAKE DETECTION: A PILOT STUDY
Songjun Cao, Tencent Youtu Lab, China; Yuqi Li, Tencent Youtu Lab, Fudan University, China; Yunpeng Luo, Tencent Youtu Lab, China; Jianjun Yin, Fudan University, China; Long Ma, Tencent Youtu Lab, China
Thu, 7 May, 16:50 - 17:10

IFS-L5.2: DIFF-IML : TOWARDS THE DIFFUSION-BASED REAL-WORLD IMAGE MANIPULATION LOCALIZATION
Dayong Wang, Wanyi Zhuang, Qi Chu, Tao Gong, Bin Liu, Nenghai Yu, University of Science and Technology of China, China
Thu, 7 May, 17:10 - 17:30

IFS-L5.3: TARGETED POOLED LATENT-SPACE STEGANALYSIS APPLIED TO GENERATIVE STEGANOGRAPHY, WITH A FIX
Etienne Levecque, Troyes University of Technology, LIST3N lab, France; Aurélien Noirault, UMR 9189 CRIStAL University of Lille, CNRS, Centrale Lille, France; Tomas Pevny, Artificial Intelligence Center, Czech Technical University, Czechia; Jan Butora, UMR 9189 CRIStAL University of Lille, CNRS, Centrale Lille, France; Rémi Cogranne, Troyes University of Technology, LIST3N lab, France; Patrick Bas, UMR 9189 CRIStAL University of Lille, CNRS, Centrale Lille, France
Thu, 7 May, 17:30 - 17:50

IFS-L5.4: DRAWMARK: DEFEATING REGENERATION ATTACKS BY EMBEDDING WATERMARK INTO PREDICTED NOISE OF DIFFUSION MODELS
Cao Zixuan, Liao Xin, Wu Yufeng, Hunan University, China; Wang Junjie, Institute of Software Chinese Academy of Sciences, China; Wu Xiaoshuai, Hunan University, China
Thu, 7 May, 17:50 - 18:10

IFS-L5.5: Impact of Phonetics on Speaker Identity in Adversarial Voice Attack
Daniyal Kabir Dar, Qiben Yan, Li Xiao, Arun Ross, Michigan State University, United States of America
Thu, 7 May, 18:10 - 18:30

IFS-L5.6: ATTRIBUTE DRIVEN W SPACE FOR QUERY LIMITED FACE TEMPLATE INVERSION
Zhiheng Zhou, Zixuan Shen, Longchen Dai, Peipeng Yu, Kaikai Gan, Zhihua Xia, Jinan University, China