The great economic values of deep neural networks (DNNs) urge AI enterprises to protect their intellectual property (IP) for these models. Recently, proof-of-training (PoT) has been proposed as a promising solution to DNN IP protection, through which AI enterprises can utilize the record of DNN training process as their ownership proof. To prevent attackers from forging ownership proof, a secure PoT scheme should be able to distinguish honest training records from those forged by attackers. Although existing PoT schemes provide various distinction criteria, these criteria are based on intuitions or observations. The effectiveness of these criteria lacks clear and comprehensive analysis, resulting in existing schemes initially deemed secure being swiftly compromised by simple ideas. In this paper, we make the first move to identify distinction criteria in the style of formal methods, so that their effectiveness can be explicitly demonstrated. Specifically, we conduct systematic modeling to cover a wide range of attacks and then theoretically analyze the distinctions between honest and forged training records. The analysis results not only induce a universal distinction criterion, but also provide detailed reasoning to demonstrate its effectiveness in defending against attacks covered by our model. Guided by the criterion, we propose a generic PoT construction that can be instantiated into concrete schemes. This construction sheds light on the realization that trajectory matching algorithms, previously employed in data distillation, possess significant advantages in PoT construction. Experimental results demonstrate that our scheme can resist attacks that have compromised existing PoT schemes, which corroborates its superiority in security.
HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);University of Chinese Academy of Sciences(中国科学院大学);Boston University(波士顿大学);University of Oregon(俄勒冈大学)
FedSOV: Federated Model Secure Ownership Verification with Unforgeable Signature
Sun Yat-sen University(中山大学);University of Electronic Science and Technology of China(电子科技大学);WeBank(微众银行);The Hong Kong University of Science and Technology(香港科技大学)
Revisiting Black-Box Model Ownership Verification through Information Theory
Anhui University of Technology(安徽工业大学);University of Cambridge(剑桥大学);Microsoft(微软);Nanjing University of Posts and Telecommunications(南京邮电大学);Tylogi AI Lab(Tylogi AI实验室);The Hong Kong Polytechnic University(香港理工大学);Southeast University(东南大学)
FedZKP: Federated Model Ownership Verification with Zero-knowledge Proof
Sun Yat-sen University(中山大学);University of Electronic Science and Technology of China(电子科技大学);WeBank(微众银行);The Hong Kong University of Science and Technology(香港科技大学)
SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification
School of Control and Computer Engineering(控制与计算机工程学院);North China Electric Power University(华北电力大学);Research Institute(研究院);China Unicom(中国联合网络通信集团);Technical Department(技术部)
A2-DIDM: Privacy-preserving Accumulator-enabled Auditing for Distributed Identity of DNN Model
School of Cyberspace Science and Technology, Beijing Institute of Technology(信息科学与技术学院,北京理工大学);School of AI, Beijing Institute of Technology(人工智能学院,北京理工大学);Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China(民族语言智能分析与安全治理教育部重点实验室,中央民族大学);School of Information Engineering, Minzu University of China(信息工程学院,中央民族大学);Zhongguancun Academy, Haidian, Beijing, China(中关村学院,北京市海淀区,中国)
CHIP: Chameleon Hash-based Irreversible Passport for Robust Deep Model Ownership Verification and Active Usage Control
School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电子与电气工程学院);Engineering Research Center of Digital Forensics, School of Computer Science, Nanjing University of Information Science and Technology(信息科学技术大学计算机科学学院数字取证研究中心);School of Electrical and Electronic Engineering and National Integrated Centre for Evaluation (NiCE), Nanyang Technological University(南洋理工大学电子与电气工程学院国家整合评估中心)
DSSmoothing: Toward Certified Dataset Ownership Verification for Pre-trained Language Models via Dual-Space Smoothing
North China Electric Power University(华北电力大学);Research Institute, China Unicom(中国联合研究院);Wuhan University(武汉大学);Beihang University(北京航空航天大学);Nanyang Technological University(南洋理工大学)
CertDW: Towards Certified Dataset Ownership Verification via Conformal Calibration
School of Control and Computer Engineering, North China Electric Power University(控制与计算机工程学院,华北电力大学);College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学);School of Cybersecurity, Northwestern Polytechnical University(网络安全学院,西北工业大学);Department of Computer Science, University of Maryland(计算机科学系,马里兰大学);Alibaba Group(阿里巴巴集团)
Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
Zhejiang University(浙江大学);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新区(滨江)区块链与数据安全研究院);Nanyang Technological University(南洋理工大学)
From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));South China University of Technology(华南理工大学);Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)
FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint
State Key Laboratory of Blockchain and Data Security, Zhejiang University(区块链与数据安全国家重点实验室,浙江大学);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou(杭州高新技术区(滨江)区块链与数据安全研究院,杭州);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院);Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系)
CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);School of Mathematics, Sun Yat-sen University(中山大学数学学院);Zhejiang University(浙江大学);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新区(滨江)区块链与数据安全研究院);Tsinghua University(清华大学);Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Research Center of Artificial Intelligence, Peng Cheng Laboratory(鹏城实验室人工智能研究中心)
Forging the Unforgeable: On the Feasibility of Counterfeit Watermarks in Backdoor-Based Dataset Ownership Verification
College of Cyber Security, Jinan University(济南大学网络安全学院);School of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院);School of Advanced Technology, Xi’an Jiaotong-Liverpool University(西交利物浦大学前沿技术学院)
Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing
Generative AI Lab, College of Computing;Data Science, Nanyang Technological University, Singapore;Department of Computer Science;Engineering, Texas A\&M University, USA
MOVE: Effective and Harmless Ownership Verification via Embedded External Features
Zhejiang University(浙江大学);Tsinghua University(清华大学);Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院);Nanyang Technological University(南洋理工大学);ByteDance Inc(字节跳动公司);Peng Cheng Laboratory(鹏城实验室);Sun Yat-sen University(中山大学);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新区(滨江)区块链与数据安全研究院)
Black-box Dataset Ownership Verification via Backdoor Watermarking
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);School of Information Science and Technology, Southwest Jiaotong University(西南交通大学信息科学与技术学院);Research Center of Artificial Intelligence, Peng Cheng Laboratory(鹏城实验室人工智能研究中心);Ant Group(蚂蚁集团)
PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark
State Key Laboratory of Blockchain and Data Security, Zhejiang University(浙江大学区块链与数据安全国家重点实验室);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新区(滨江)区块链与数据安全研究院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)