IFS-P2.7
Functional Invariants to Watermark Large Transformers
Pierre Fernandez, FAIR, Meta & Inria, France; Guillaume Couairon, FAIR, Meta, France; Teddy Furon, Inria, France; Matthijs Douze, FAIR, Meta, France
Session:
IFS-P2: Anonymisation, Data Privacy and Hiding Poster
Track:
Information Forensics and Security
Location:
Poster Zone 6A
Poster Board PZ-6A.7
Poster Board PZ-6A.7
Presentation Time:
Tue, 16 Apr, 13:10 - 15:10 (UTC +9)
Session Chair:
Zeki Erkin, Delft University of Technology
Session IFS-P2
IFS-P2.2: A NOVEL RESIDUAL-GUIDED LEARNING METHOD FOR IMAGE STEGANOGRAPHY
Miaoxin Ye, Dongxia Huang, Kangkang Wei, Weiqi Luo, GuangDong Province Key Laboratory of Information Security Technology, School of Computer Science and Engineering, Sun Yat-sen University, GuangZhou, China, China
IFS-P2.3: EXPLORING CONSISTENT SPATIO-TEMPORAL DISTORTION AND STABLE 3-D DCT COEFFICIENTS FOR ROBUST BLIND VIDEO WATERMARKING
Fei Zhang, Hongxia Wang, Mingze He, Ling Yang, School of Cyber Science and Engineering, Sichuan University; Key Laboratory of Data Protection and Intelligent Management (Sichuan University), Ministry of Education, China., China
IFS-P2.4: MANTICORE: AN UNSUPERVISED INTRUSION DETECTION SYSTEM BASED ON CONTRASTIVE LEARNING IN 5G NETWORKS
Lu Yuan, Jiyan Sun, Shangyuan Zhuang, Yinlong Liu, Liru Geng, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, China; Jing Zou, Peizhe Xin, State Grid Economic and Technological Research Institute Co., LTD Beijing, China, China; Weiqing Huang, Wei Ma, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, China
IFS-P2.5: INVERTEDFONTNET: FONT WATERMARKING BASED ON PERTURBING STYLE MANIFOLD
Nan Sun, Chenxin Zhao, Sijing Xie, Hefei Ling, Huazhong University of Science and Technology, China
IFS-P2.6: SE-SIS: shadow-embeddable lossless secret image sharing for greyscale images
Zikai Xu, Bin Liu, Fei Hu, Weihai Li, Nenghai Yu, University of Science and Technology of China, China
IFS-P2.7: Functional Invariants to Watermark Large Transformers
Pierre Fernandez, FAIR, Meta & Inria, France; Guillaume Couairon, FAIR, Meta, France; Teddy Furon, Inria, France; Matthijs Douze, FAIR, Meta, France
IFS-P2.8: DROPFL: CLIENT DROPOUT ATTACKS AGAINST FEDERATED LEARNING UNDER COMMUNICATION CONSTRAINTS
Wenjun Qian, Qingni Shen, Haoran Xu, Xi Huang, Zhonghai Wu, Peking University, China
IFS-P2.9: COMMUNICATION-EFFICIENT LAPLACE MECHANISM FOR DIFFERENTIAL PRIVACY VIA RANDOM QUANTIZATION
Ali Moradi Shahmiri, Sharif University of Technology, Iran (Islamic Republic of); Chih Wei Ling, Cheuk Ting Li, The Chinese University of Hong Kong, Hong Kong
IFS-P2.10: RENYI DIFFERENTIAL PRIVACY IN THE SHUFFLE MODEL: ENHANCED AMPLIFICATION BOUNDS
E Chen, Zhejiang Lab, China; Yang Cao, Hokkaido University, Japan; Yifei Ge, Xi'an Jiaotong-Liverpool University, China
IFS-P2.11: UNINTENDED MEMORIZATION IN LARGE ASR MODELS, AND HOW TO MITIGATE IT
Lun Wang, Om Thakkar, Rajiv Mathews, Google, United States of America
IFS-P2.12: SPEAKER ANONYMIZATION USING NEURAL AUDIO CODEC LANGUAGE MODELS
Michele Panariello, EURECOM, France; Francesco Nespoli, Microsoft, United Kingdom of Great Britain and Northern Ireland; Massimiliano Todisco, Nicholas Evans, EURECOM, France
Contacts