mlsanityData to 14 Oct 2026

Tokenized Model: A Blockchain-Empowered Decentralized Model Ownership Verification Platform

arXiv 2312.00048 ↗First posted 27 Nov 2023cs.CR cs.LGcited by 0

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

With the development of practical deep learning models like generative AI, their excellent performance has brought huge economic value. For instance, ChatGPT has attracted more than 100 million users in three months. Since the model training requires a lot of data and computing power, a well-performing deep learning model is behind a huge effort and cost. Facing various model attacks, unauthorized use and abuse from the network that threaten the interests of model owners, in addition to considering legal and other administrative measures, it is equally important to protect the model's copyright from the technical means. By using the model watermarking technology, we point out the possibility of building a unified platform for model ownership verification. Given the application history of blockchain in copyright verification and the drawbacks of a centralized third-party, this paper considers combining model watermarking technology and blockchain to build a unified model copyright protection platform. By a new solution we called Tokenized Model, it protects the model's copyright by reliable ownership record and verification mechanism. It also promotes the financial value of model by constructing the model's transaction process and contribution shares of a model. In the typical case study, we also study the various performance under usual scenario to verify the effectiveness of this platform.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 13 of its 16 references that are in the map. First posted on arXiv 27 Nov 2023.

Builds on

13 of 16 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark17 May
  2. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Models27 Mar
  3. 2021FedIPR: Ownership Verification for Federated Deep Neural Network Models27 Sep

Other references · 10

  1. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
  2. 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examplescited by 167
  3. 2020A Blockchain-based Decentralized Federated Learning Framework with Committee Consensuscited by 84
  4. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 42
  5. 2022FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Modelcited by 30
  6. 2021Non-Fungible Token (NFT): Overview, Evaluation, Opportunities and Challengescited by 25
  7. 2021Model Extraction and Defenses on Generative Adversarial Networkscited by 8
  8. 2020A Blockchain-based Platform Architecture for Multimedia Data Managementcited by 1
  9. 2020DCDChain: A Credible Architecture of Digital Copyright Detection Based on Blockchaincited by 1
  10. 2021Securing music sharing platforms: A Blockchain-Based Approachcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models
  2. 2026Membership is Ownership: A Robust Ownership Verification Framework for Diffusion Models
  3. 2023Turn Passive to Active: A Survey on Active Intellectual Property Protection of Deep Learning Models
  4. 2024Proof of Quality: A Costless Paradigm for Trustless Generative AI Model Inference on Blockchains
  5. 2023Performance-lossless Black-box Model Watermarking
  6. 2024Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
  7. 2021Regulating Ownership Verification for Deep Neural Networks: Scenarios, Protocols, and Prospects
  8. 2024Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging