mlsanityData to 14 Oct 2026

Adversarial Frontier Stitching for Remote Neural Network Watermarking

arXiv 1711.01894 ↗First posted 6 Nov 2017cs.CRcited by 118

Not on the map. Why?

Cited by 39 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The state of the art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements. Recently, [35, 22] proposed to watermark convolutional neural networks for image classification, by embedding information into their weights. While this is a clear progress towards model protection, this technique solely allows for extracting the watermark from a network that one accesses locally and entirely. Instead, we aim at allowing the extraction of the watermark from a neural network (or any other machine learning model) that is operated remotely, and available through a service API. To this end, we propose to mark the model's action itself, tweaking slightly its decision frontiers so that a set of specific queries convey the desired information. In the present paper, we formally introduce the problem and propose a novel zero-bit watermarking algorithm that makes use of adversarial model examples. While limiting the loss of performance of the protected model, this algorithm allows subsequent extraction of the watermark using only few queries. We experimented the approach on three neural networks designed for image classification, in the context of MNIST digit recognition task.

Key facts. Cited by 118 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 30; 2022: 26; 2023: 30; 2024: 16; 2025: 11; 2026: 5.

118 papers.

Sort:

By area:

  1. 2023A Recipe for Watermarking Diffusion Modelscited by 141
  2. 2023Protecting Language Generation Models via Invisible Watermarkingcited by 90
  3. 2021Protecting Intellectual Property of Language Generation APIs with Lexical Watermarkcited by 84
  4. 2021SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)cited by 69
  5. 2023Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermarkcited by 67
  6. 2022Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbationscited by 61
  7. 2021Deep Model Intellectual Property Protection via Deep Watermarkingcited by 54
  8. 2021Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorizationcited by 52
  9. 2022Watermarking Pre-trained Language Models with Backdooringcited by 50
  10. 2021Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attackcited by 46
  11. 2021Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Modelscited by 46
  12. 2022SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoderscited by 45
38 more
  1. 2023Watermarking Diffusion Modelcited by 37
  2. 2023HuRef: HUman-REadable Fingerprint for Large Language Modelscited by 34
  3. 2022Distillation-Resistant Watermarking for Model Protection in NLPcited by 30
  4. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  5. 2024Watermarking Techniques for Large Language Models: A Surveycited by 23
  6. 2023Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Processcited by 19
  7. 2021You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownershipcited by 18
  8. 2022Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooringcited by 17
  9. 2023False Claims against Model Ownership Resolutioncited by 17
  10. 2021Teacher Model Fingerprinting Attacks Against Transfer Learningcited by 16
  11. 2023GrOVe: Ownership Verification of Graph Neural Networks using Embeddingscited by 16
  12. 2024ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Modelscited by 16
  13. 2021A Protection Method of Trained CNN Model with Secret Key from Unauthorized Accesscited by 15
  14. 2023Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protectioncited by 14
  15. 2021AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryptioncited by 13
  16. 2022Cosine Model Watermarking Against Ensemble Distillationcited by 13
  17. 2022Image and Model Transformation with Secret Key for Vision Transformercited by 12
  18. 2023Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attackscited by 12
  19. 2022Watermarking Pre-trained Encoders in Contrastive Learningcited by 11
  20. 2023Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Servicecited by 11
  21. 2021Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Keycited by 10
  22. 2023What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networkcited by 10
  23. 2023Towards Robust Model Watermark via Reducing Parametric Vulnerabilitycited by 10
  24. 2023Wide Flat Minimum Watermarking for Robust Ownership Verification of GANscited by 10
  25. 2023Who Leaked the Model? Tracking IP Infringers in Accountable Federated Learningcited by 10
  26. 2021Safe Distillation Boxcited by 9
  27. 2024Ungeneralizable Examplescited by 9
  28. 2024RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guaranteescited by 8
  29. 2023When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protectioncited by 7
  30. 2024Probabilistically Robust Watermarking of Neural Networkscited by 7
  31. 2024Say No to Freeloader: Protecting Intellectual Property of Your Deep Modelcited by 7
  32. 2021Robust Black-box Watermarking for Deep NeuralNetwork using Inverse Document Frequencycited by 6
  33. 2021Detect and remove watermark in deep neural networks via generative adversarial networkscited by 6
  34. 2021Evaluating the Robustness of Trigger Set-Based Watermarks Embedded in Deep Neural Networkscited by 6
  35. 2023Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Modelscited by 6
  36. 2024Box-Free Model Watermarks Are Prone to Black-Box Removal Attackscited by 6
  37. 2021Protecting the Intellectual Properties of Deep Neural Networks with an Additional Class and Steganographic Imagescited by 5
  38. 2021Fostering the Robustness of White-Box Deep Neural Network Watermarks by Neuron Alignmentcited by 5

50 most cited of 118 All 118 (JSON)