IFS-P6.10
NOISE MASKING ATTACKS AND DEFENSES FOR PRETRAINED SPEECH MODELS
Matthew Jagielski, Om Thakkar, Lun Wang, Google, United States of America
Session:
IFS-P6: IFS General Poster
Track:
Information Forensics and Security
Location:
Poster Zone 2B
Poster Board PZ-2B.10
Poster Board PZ-2B.10
Presentation Time:
Thu, 18 Apr, 16:30 - 18:30 (UTC +9)
Session Chair:
Paolo Bestagini, Politecnico di Milano
Session IFS-P6
IFS-P6.1: FuzzLLM: A Novel and Universal Fuzzing Framework for Proactively Discovering Jailbreak Vulnerabilities in Large Language Models
Dongyu Yao, Jianshu Zhang, Wuhan University, China; Ian Harris, University of California Irvine, United States of America; Marcel Carlsson, Lootcore, Sweden
IFS-P6.2: XMP: A Cross-Attention Multi-Scale Performer for File Fragment Classification
Jeong Gyu Park, Sisung Liu, Je Hyeong Hong, Hanyang University, Korea, Republic of
IFS-P6.3: A FAST, PERFORMANT, SECURE DISTRIBUTED TRAINING FRAMEWORK FOR LLM
Wei Huang, Yinggui Wang, Anda Cheng, Aihui Zhou, Chaofan Yu, Lei Wang, Ant Group, China
IFS-P6.4: DETECTION AND ATTRIBUTION OF MODELS TRAINED ON GENERATED DATA
Ge Han, Shandong University, China; Ahmed Salem, Azure Research, United Kingdom of Great Britain and Northern Ireland; Zheng Li, CISPA Helmholtz Center for Information Security, Germany; Shanqing Guo, Shandong University, China; Michael Backes, Yang Zhang, CISPA Helmholtz Center for Information Security, Germany
IFS-P6.5: SEMANTIC SECURITY: A DIGITAL WATERMARK METHOD FOR IMAGE SEMANTIC PRESERVATION
Tianwei Zuo, Yiping Duan, Qiyuan Du, Xiaoming Tao, Tsinghua University, China
IFS-P6.6: CRYPTO-MINE: Cryptanalysis via Mutual Information Neural Estimation
Benjamin D. Kim, University of Illinois Urbana-Champaign, United States of America; Vipindev Adat Vasudevan, Jongchan Woo, Massachusetts Institute of Technology, United States of America; Alejandro Cohen, Technion, Israel; Rafael G. L. D'Oliveira, Clemson University, United States of America; Thomas Stahlbuhk, MIT Lincoln Laboratory, United States of America; Muriel Médard, Massachusetts Institute of Technology, United States of America
IFS-P6.7: EFFICIENT CODED MULTI-PARTY COMPUTATION AT EDGE NETWORKS
Elahe Vedadi, UIC, United States of America; Yasaman Keshtkarjahromi, Seagate Technology, United States of America; Hulya Seferoglu, UIC, United States of America
IFS-P6.8: GI-PIP: DO WE REQUIRE IMPRACTICAL AUXILIARY DATASET FOR GRADIENT INVERSION ATTACKS?
Yu Sun, Gaojian Xiong, Xianxun Yao, Kailang Ma, Jian Cui, Beihang University, China
IFS-P6.9: VOICE ANONYMIZATION FOR ALL - BIAS EVALUATION OF THE VOICE PRIVACY CHALLENGE BASELINE SYSTEMS
Anna Leschanowsky, Fraunhofer IIS, Germany; Ünal Ege Gaznepoglu, Nils Peters, International Audio Laboratories Erlangen, Germany
IFS-P6.10: NOISE MASKING ATTACKS AND DEFENSES FOR PRETRAINED SPEECH MODELS
Matthew Jagielski, Om Thakkar, Lun Wang, Google, United States of America
IFS-P6.11: Analysis and Utilization of Hidden Information in Model Inversion Attacks
Zeping Zhang, Xiaowen Wang, Jie Huang, Shuaishuai Zhang, southeast university, China
IFS-P6.12: Synthbuster: Towards Detection of Diffusion Model Generated Images
Quentin Bammey, Université Paris-Saclay Ringgold standard institution - ENS Paris-Saclay, Centre Borelli Gif-sur-Yvette, Île-de-France France
Contacts