mlsanityData to 14 Oct 2026

ZKROWNN: Zero Knowledge Right of Ownership for Neural Networks

arXiv 2309.06779 ↗First posted 13 Sep 2023cs.CRcited by 6

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

Abstract (arXiv)

Training contemporary AI models requires investment in procuring learning data and computing resources, making the models intellectual property of the owners. Popular model watermarking solutions rely on key input triggers for detection; the keys have to be kept private to prevent discovery, forging, and removal of the hidden signatures. We present ZKROWNN, the first automated end-to-end framework utilizing Zero-Knowledge Proofs (ZKP) that enable an entity to validate their ownership of a model, while preserving the privacy of the watermarks. ZKROWNN permits a third party client to verify model ownership in less than a second, requiring as little as a few KBs of communication.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 10 of its 25 references that are in the map. First posted on arXiv 13 Sep 2023.

Builds on

10 of 25 references.

References · 10

  1. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
  2. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  3. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
  4. 2017Recent Trends in Deep Learning Based Natural Language Processingcited by 263
  5. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  6. 2021A survey of deep neural network watermarking techniquescited by 73
  7. 2020Model Watermarking for Image Processing Networkscited by 56
  8. 2018Digital Watermarking for Deep Neural Networkscited by 39
  9. 2018DeepMarks: A Digital Fingerprinting Framework for Deep Neural Networkscited by 26
  10. 2015When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognitioncited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 3; 2026: 1.

6 papers.

  1. 2023Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Surveycited by 18
  2. 2024Watermarking Large Language Models and the Generated Content: Opportunities and Challengescited by 2
  3. 2025Optimizing Privacy-Preserving Primitives to Support LLM-Scale Applicationscited by 1
  4. 2025ZK-WAGON: Imperceptible Watermark for Image Generation Models using ZK-SNARKscited by 1
  5. 2025Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesigncited by 0
  6. 2026Internalising the Identity Primitive: Cryptographic Individuality for an Autonomous Agent on a Public Blockchaincited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023OVLA: Neural Network Ownership Verification using Latent Watermarks
  2. 2024Revisiting Black-Box Model Ownership Verification through Information Theory
  3. 2021Regulating Ownership Verification for Deep Neural Networks: Scenarios, Protocols, and Prospects
  4. 2021Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization
  5. 2022Knowledge-Free Black-Box Watermark and Ownership Proof for Image Classification Neural Networks
  6. 2021Ownership Verification of DNN Architectures via Hardware Cache Side Channels
  7. 2025Watermarking Graph Neural Networks via Explanations for Ownership Protection
  8. 2024Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution