mlsanityData to 14 Oct 2026

PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarking

arXiv 2505.12296 ↗First posted 18 May 2025cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Our evaluation shows that PoLO achieves 99% watermark detection accuracy for ownership verification, while preserving data privacy and cutting verification costs to just 1.5--10% of traditional methods. Forging PoLO demands 1.1--4× more resources than honest proof generation, with the original proof retaining over 90% detection accuracy even after attacks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 66 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

33 of 66 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Wide Residual Networkscited by 3,070
  4. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,127
  5. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
  6. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  7. 2019A Survey on Distributed Machine Learningcited by 188
  8. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 171
  9. 2023A Survey of Text Watermarking in the Era of Large Language Modelscited by 112
  10. 2021Proof-of-Learning: Definitions and Practicecited by 84
  11. 2021DVMark: A Deep Multiscale Framework for Video Watermarkingcited by 46
  12. 2019REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Datacited by 44
21 more
  1. 2023Detecting Voice Cloning Attacks via Timbre Watermarkingcited by 44
  2. 2024Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attributioncited by 40
  3. 2021FedIPR: Ownership Verification for Federated Deep Neural Network Modelscited by 36
  4. 2023PromptCARE: Prompt Copyright Protection by Watermark Injection and Verificationcited by 32
  5. 2022FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Modelcited by 30
  6. 2024UnMarker: A Universal Attack on Defensive Image Watermarkingcited by 24
  7. 2021"Adversarial Examples" for Proof-of-Learningcited by 20
  8. 2023Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscationcited by 20
  9. 2021Gradient Leakage Attack Resilient Deep Learningcited by 18
  10. 2023IronForge: An Open, Secure, Fair, Decentralized Federated Learningcited by 15
  11. 2023Moderating Model Marketplaces: Platform Governance Puzzles for AI Intermediariescited by 9
  12. 2020Golden Grain: Building a Secure and Decentralized Model Marketplace for MLaaScited by 7
  13. 2025Dataset Ownership Verification in Contrastive Pre-trained Modelscited by 6
  14. 2024DeepEclipse: How to Break White-Box DNN-Watermarking Schemescited by 5
  15. 2021Secure Watermark for Deep Neural Networks with Multi-task Learningcited by 4
  16. 2023Split Unlearningcited by 4
  17. 2024Is Your AI Truly Yours? Leveraging Blockchain for Copyrights, Provenance, and Lineagecited by 4
  18. 2024Proof-of-Learning with Incentive Securitycited by 4
  19. 2024Maximizing NFT Incentives: References Make You Richcited by 2
  20. 2024Towards Understanding and Enhancing Security of Proof-of-Training for DNN Model Ownership Verificationcited by 2
  21. 2019The Attack of the Clones Against Proof-of-Authoritycited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Forging the Unforgeable: On the Feasibility of Counterfeit Watermarks in Backdoor-Based Dataset Ownership Verification
  2. 2023Puppy: A Publicly Verifiable Watermarking Protocol
  3. 2025PVMark: Enabling Public Verifiability for LLM Watermarking Schemes
  4. 2024Revisiting Black-Box Model Ownership Verification through Information Theory
  5. 2025FLClear: Visually Verifiable Multi-Client Watermarking for Federated Learning
  6. 2026RaMark: Radioactive Watermarking for Generated Tabular Data
  7. 2025Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models
  8. 2025MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarks