mlsanityData to 7 Oct 2026

Anti-Neuron Watermarking: Protecting Personal Data Against Unauthorized Neural Networks

arXiv 2109.09023 ↗First posted 18 Sep 2021cs.CR cs.LG cs.MMcited by 4

Not on the map. Why?

Abstract (arXiv)

We study protecting a user's data (images in this work) against a learner's unauthorized use in training neural networks. It is especially challenging when the user's data is only a tiny percentage of the learner's complete training set. We revisit the traditional watermarking under modern deep learning settings to tackle the challenge. We show that when a user watermarks images using a specialized linear color transformation, a neural network classifier will be imprinted with the signature so that a third-party arbitrator can verify the potentially unauthorized usage of the user data by inferring the watermark signature from the neural network. We also discuss what watermarking properties and signature spaces make the arbitrator's verification convincing. To our best knowledge, this work is the first to protect an individual user's data ownership from unauthorized use in training neural networks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 25 of its 55 references that are in the map. First posted on arXiv 18 Sep 2021.

Builds on

25 of 55 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2016Wide Residual Networkscited by 3,057
  8. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  9. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  10. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  11. 2019When Does Label Smoothing Help?cited by 985
  12. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
13 more
  1. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 492
  2. 2017Deep Layer Aggregationcited by 436
  3. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 265
  4. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 183
  5. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  6. 2021Dataset Inference: Ownership Resolution in Machine Learningcited by 115
  7. 2019Overlearning Reveals Sensitive Attributescited by 74
  8. 2020Radioactive data: tracing through trainingcited by 67
  9. 2020Model Watermarking for Image Processing Networkscited by 49
  10. 2020Passport-aware Normalization for Deep Model Protectioncited by 42
  11. 2018Digital Watermarking for Deep Neural Networkscited by 37
  12. 2020Open-sourced Dataset Protection via Backdoor Watermarkingcited by 30
  13. 2017Privacy Risk in Machine Learning: Analyzing the Connection to Overfittingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Instance-Level Data-Use Auditing of Visual ML Modelscited by 4
  2. 2025Evading Data Provenance in Deep Neural Networkscited by 2
  3. 2026AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspectivecited by 1
  4. 2026Moir'e Video Authentication: A Physical Signature Against AI Video Generationcited by 0