Dataset Watermarking

Ask about this topic

Overview

Dataset watermarking studies how to mark datasets so their ownership or use can later be verified, including when only a trained model’s outputs are accessible. Approaches include trigger-based or backdoor marks, statistical changes to data distributions, and text-preserving cues, with methods tailored to tabular, image, and language data. Verification may test for the mark directly in data or probe downstream models using statistical tests, often across benchmark tasks and black-box settings. The central tension is making marks robust to removal, transformations, and retraining while maintaining data fidelity, model utility, and reliable control of false positives.

Latest papers

CardsList

21 papers1 paper in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

  1. SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing

    Oct 22, 2026Sy-Tuyen Ho, Anirudh Satheesh, Soham Chawathe +4Dataset WatermarkingDiffusion Model Watermarking

    University of Maryland · All Purpose AI

  2. ZK-Trace: Certified Collusion Tracing with Zero-Knowledge Credentials for Federated GNSS Interference Monitoring

    Sep 8, 2026Redwanul Karim, Nisha L. Raichur, Lucas Heublein +3Dataset WatermarkingFederated Learning

    Fraunhofer Institute for Integrated Circuits IIS, 90411 Nürnberg, Germany

  3. Rent-a-RAG: Embedding-Space Watermarks for Auditing Third-Party RAG

    Sep 3, 2026Alexandr Goultiaev Tolstokorov, Kyriakos Mouratidis, Javad Dogani +1Dataset WatermarkingRAG Security

    IMDEA Networks Institute, Madrid, Spain · Universidad Carlos III de Madrid, Madrid, Spain · Singapore Management University, Singapore

  4. Minimax bounds for watermarked and masked recursive discrete distribution estimation

    Aug 31, 2026Millen Kanabar, Michael GastparDataset WatermarkingMinimax Estimation

    School of Computer and Communication Sciences, EPFL, Switzerland

  5. Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning

    Aug 20, 2026Xinyun Liu, Zhi Lu, Yu Chen +1Federated LearningDataset Watermarking

    Department of Applied Computing, Michigan Technological University, Houghton, MI 49931, USA · School of Computing, National University of Singapore, Singapore, 119077, Singapore · Department of Electrical and Computer Engineering, Binghamton University, Binghamton, NY 13902, USA

  6. Reversible Unlearnable Examples: Towards the Copyright Protection in Deep Learning Era

    Aug 6, 2026Binze Wang, Jinyu Tian, Xingrun Wang +2Dataset WatermarkingUnlearnable Examples

    School of Computer Science and Engineering, Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, China · School of Computer Science and Artificial Intelligence of FoShan University, FoShan 528225, China · Faculty of Applied Sciences of the Macao Polytechnic University, Macau, China

  7. SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding

    Aug 4, 2026Wei Song, Yuxin Cao, Zhenchang Xing +4Dataset WatermarkingRobust Watermarking

    University of New South Wales, Australia · National University of Singapore, Singapore · CSIRO’s Data61, Australia

  8. Secure AI Watermarking Framework for IP Protection in Multi-Tenant Cloud Platforms

    Aug 1, 2026M Anjan Kumar, Kishor Kumar Gajula, Ch PrathimaDataset WatermarkingCloud Computing

    Department of Computer Science and Engineering , Viswam Engineering College, Madanapalle, Andhra Pradesh , India · Department of Computer Science and Engineering , Mother Theresa Institute Of Engineering and Technology, Peddapalli, Telangana, India · Department of Computer Science and Engineering , Mohan Babu University, Tirupathi, Andhra Pradesh ; India

  9. Observation-Level Watermarking and Detection for Tabular Data

    Jul 12, 2026Dongyu Cui, Xuan BiDataset WatermarkingRobust Watermarking

    School of Statistics, University of Minnesota · Carlson School of Management, University of Minnesota

  10. RaMark: Radioactive Watermarking for Generated Tabular Data

    Jul 10, 2026Xin Che, Lingyang Chu, Qiqi Zhang +3Data ProvenanceDataset Watermarking

    McMaster University Hamilton, Canada · York University Toronto, Canada · Duke University Durham, United States

  11. Efficient, Robust, and Anti-Collusion Fingerprinting of Image Diffusion Models

    Jun 11, 2026Jianwei Fei, Yunshu Dai, Zhihua Xia +4Dataset WatermarkingT2I Diffusion Models

    University of Florence, Florence, Italy · Shenzhen Campus of Sun Yat-sen University, Shenzhen, China · College of Cyber Security, Jinan University, Guangzhou, China +2

  12. T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking

    Jun 10, 2026Jian-Ping Mei, Weibin Zhang, Ao Yao +2Watermark RemovalModel Extraction Attacks

    College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, 310023 China

  13. Do Modern Post-Hoc Watermarking Methods Beat Broken-Arrows?

    May 26, 2026Enoal Gesny, Eva GiboulotWatermark RemovalDataset Watermarking

    Inria Rennes, France

  14. The Economics of Model Collapse: Equilibrium, Welfare, and Optimal Provenance Subsidies in Synthetic Data Markets

    May 19, 2026Gustav Olaf Yunus Laitinen-Fredriksson Lundström-ImanovData ProvenanceDataset Watermarking

    Department of Economics Stockholm University Stockholm, Sweden

  15. Dataset Watermarking for Closed LLMs with Provable Detection

    May 7, 2026Pengrun Huang, Kamalika Chaudhuri, Yu-Xiang WangDataset WatermarkingLLM Auditing

    Preprint. Under review.

  16. Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning

    May 3, 2026Zhiyang Dai, Yansong Gao, Boyu Kuang +5Contrastive LearningDataset Watermarking

    School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China · University of Western Australia, Perth, Australia · College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China +3

  17. Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection

    Apr 12, 2026Xinlei Guan, David Arosemena, Tejaswi Dhandu +7Digital Image ForensicsDataset Watermarking

    Kean University, Union, NJ 07083 USA · North Dakota State University, Fargo, ND 58102 USA · McGill University, Montréal, QC H3A 0G4, Canada +2

  18. Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique

    Oct 7, 2025Yanming Li, Cédric Eichler, Nicolas Anciaux +3Data ProvenanceDataset Watermarking

    PETSCRAFT · Petscraft, Inria, Palaiseau, France · INSA CVL, Bourges, France +6

  19. CertDW: Towards Certified Dataset Ownership Verification via Conformal Calibration

    Jun 16, 2025Ting Qiao, Yiming Li, Jianbin Li +5Dataset WatermarkingRobust Watermarking

    School of Control and Computer Engineering, North China Electric Power University, Beijing,102206, China · College of Computing and Data Science, Nanyang Technological University, Singapore, 639798, Singapore · School of Cybersecurity, Northwestern Polytechnical University, Xi’an, 710072, China +2

  20. CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking

    Mar 2, 2025Yiming Li, Kaiying Yan, Jiawen Diao +4Speaker VerificationDataset Watermarking

    College of Computing and Data Science, Nanyang Technological University, Singapore, 639798, Singapore · School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, 200030, China · Beijing Electronic Science and Technology Institute, Beijing, 100070, China +4

  21. Watermarking Continuous Tabular Data Generation

    May 22, 2024Hengzhi He, Peiyu Yu, Junpeng Ren +2Dataset WatermarkingRobust Watermarking