IFS-P10: Model Ownership, Provenance, and Stealthy Attacks
Poster
Thu, 7 May, 09:00 - 11:00
Location: Poster Area 22
Session Type: Poster
Session Chair: Sara Mandelli, Politecnico di Milano
Track: Information Forensics and Security [IF]
Click the to view the manuscript on IEEE Xplore Open Preview
 

IFS-P10.1: FORGETMARK: STEALTHY FINGERPRINT EMBEDDING VIA TARGETED UNLEARNING IN LANGUAGE MODELS
Zhenhua Xu, Zhejiang University, China; Haobo Zhang, Binjiang Institute of Zhejiang University, China; Zhebo Wang, Zhejiang University, China; Qichen Liu, Binjiang Institute of Zhejiang University, China; Haitao Xu, Wenpeng Xing, Meng Han, Zhejiang University, China
 

IFS-P10.2: ATTENTION-GUIDED DYNAMIC COMPENSATION SAMPLING FOR ROBUST INVERSION-BASED DIFFUSION WATERMARKING
Yanlin Huo, Xuehu Yan, Zhankai Li, Tao Liu, Feng Chen, Yuliang Lu, National University of Defense Technology, China
 

IFS-P10.3: GS-MARK: DEEP ROBUST WATERMARKING FOR GRAPH SIGNALS
Jiasen Li, Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences; State Key Laboratory of Cyberspace Security Defense, China; Yanwei Liu, Institute of Information Engineering, Chinese Academy of Sciences; State Key Laboratory of Cyberspace Security Defense, China; Pengzhen Chen, Zhuoyi Shang, Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences; State Key Laboratory of Cyberspace Security Defense, China; Xiaoyan Gu, Institute of Information Engineering, Chinese Academy of Sciences;School of Cyber Security, University of Chinese Academy of Sciences;State Key Laboratory of Cyberspace Security Defense, China
 

IFS-P10.4: S3-3DGS: STEERING SPHERICAL-HARMONIC SUBSPACES FOR SECURE 3DGS WATERMARKING
Wenhui Ma, Yuhui He, Yuhang Guo, Linlin Shen, Jinbao Wang, Shenzhen University, China
 

IFS-P10.5: MARKSWEEP: A NO-BOX REMOVAL ATTACK ON AI-GENERATED IMAGE WATERMARKING VIA NOISE INTENSIFICATION AND FREQUENCY-AWARE DENOISING
Jie Cao, Zelin Zhang, Qi Li, Jianbing Ni, Queen's University, Canada
 

IFS-P10.6: Selective Poisoning: Enhancing Backdoor Attacks on Graph Neural Networks with Limited Samples
Tianbo Zhang, Southeast University, China; Luoyu Mei, City University of Hong Kong, Hong Kong; Tongwei Liu, Aibo Song, Southeast University, China
 

IFS-P10.7: NOT JUST DETECTION: ALIGNED-DRIVEN PURIFICATION OF INDIRECT PROMPT INJECTION FOR RELIABLE AGENT INTERACTION
Qingxin Xiao, Boyang Zhang, Ziqian Zeng, Zhengle Ding, Xin Cheng, Lingwei Dang, Jinhui Wu, South China University of Technology, China; Yangyang Zhao, Changsha University of Science and Technology, China; Qingyao Wu, South China University of Technology, China
 

IFS-P10.8: IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis
Lingyun Zhang, Fudan University, China; Yu Xie, Purple Mountain Laboratories, China; Ping Chen, Fudan University, China
 

IFS-P10.9: TriFusion: A Self-Supervised Learning Enhanced Dual-Level Multimodal Framework for Traffic Classification
Haodong Yue, Haozhen Zhang, Xi Xiao, Tsinghua University, China; Le Yu, Nanjing University of Posts and Telecommunications, China; Guangwu Hu, Shenzhen Institute of Information Technology, China; Qing Li, Peng Cheng Laboratory, China
 

IFS-P10.10: GRADERAG: BLACK-BOX SEMANTIC PATH INJECTION ATTACKS ON GRAPH RAG SYSTEMS
Guoli Zhao, Junze Hu, Haoran Yang, Institute of Information Engineering, University of Chinese Academy of Sciences, China; Zhihu Zhao, College of Computer Engineering and Software, Taiyuan University of Technology, China; Yimo Ren, Yubo Li, Hongsong Zhu, Institute of Information Engineering, University of Chinese Academy of Sciences, China