mlsanityData to 7 Oct 2026

Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release

arXiv 2103.02683 ↗First posted 16 Feb 2021cs.CR cs.LGcited by 35

Not on the map. Why?

Abstract (arXiv)

Large organizations such as social media companies continually release data, for example user images. At the same time, these organizations leverage their massive corpora of released data to train proprietary models that give them an edge over their competitors. These two behaviors can be in conflict as an organization wants to prevent competitors from using their own data to replicate the performance of their proprietary models. We solve this problem by developing a data poisoning method by which publicly released data can be minimally modified to prevent others from train-ing models on it. Moreover, our method can be used in an online fashion so that companies can protect their data in real time as they release it.We demonstrate the success of our approach onImageNet classification and on facial recognition.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 16 Feb 2021.

Builds on

27 of 42 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  10. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  11. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  12. 2018Spectral Signatures in Backdoor Attackscited by 457
15 more
  1. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  2. 2017Certified Defenses for Data Poisoning Attackscited by 288
  3. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  4. 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 188
  5. 2020Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defensescited by 171
  6. 2020Witches' Brew: Industrial Scale Data Poisoning via Gradient Matchingcited by 156
  7. 2019Transferable Clean-Label Poisoning Attacks on Deep Neural Netscited by 129
  8. 2018Stronger Data Poisoning Attacks Break Data Sanitization Defensescited by 125
  9. 2020MetaPoison: Practical General-purpose Clean-label Data Poisoningcited by 114
  10. 2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 92
  11. 2018Is feature selection secure against training data poisoning?cited by 88
  12. 2020On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shapingcited by 82
  13. 2019Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attackscited by 79
  14. 2019Data Poisoning against Differentially-Private Learners: Attacks and Defensescited by 75
  15. 2019Understanding Generalization through Visualizationscited by 54

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 9; 2023: 9; 2024: 7; 2025: 3; 2026: 1.

35 papers.

Sort:

By area:

  1. 2021Adversarial Examples Make Strong Poisonscited by 115
  2. 2021Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratchcited by 98
  3. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  4. 2021Availability Attacks Create Shortcutscited by 60
  5. 2022Autoregressive Perturbations for Data Poisoningcited by 45
  6. 2021CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoningcited by 39
  7. 2023Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compressioncited by 39
  8. 2022Robust Unlearnable Examples: Protecting Data Against Adversarial Learningcited by 34
  9. 2022Indiscriminate Data Poisoning Attacks on Neural Networkscited by 24
  10. 2023Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attackscited by 23
  11. 2023What Can We Learn from Unlearnable Datasets?cited by 21
  12. 2025Data Poisoning in Deep Learning: A Surveycited by 20
23 more
  1. 2022Self-Ensemble Protection: Training Checkpoints Are Good Data Protectorscited by 19
  2. 2023The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Modelscited by 19
  3. 2024Poison-splat: Computation Cost Attack on 3D Gaussian Splattingcited by 17
  4. 2021Fooling Adversarial Training with Inducing Noisecited by 12
  5. 2022Can Adversarial Training Be Manipulated By Non-Robust Features?cited by 12
  6. 2024Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneouslycited by 12
  7. 2022Data Isotopes for Data Provenance in DNNscited by 11
  8. 2024Disguised Copyright Infringement of Latent Diffusion Modelscited by 10
  9. 2024ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purificationcited by 9
  10. 2024Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractorscited by 8
  11. 2021Disrupting Model Training with Adversarial Shortcutscited by 7
  12. 2022Execute Order 66: Targeted Data Poisoning for Reinforcement Learningcited by 7
  13. 2022Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformationscited by 7
  14. 2023Unlearnable Graph: Protecting Graphs from Unauthorized Exploitationcited by 5
  15. 2023Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Drivingcited by 5
  16. 2023Towards Generalizable Data Protection With Transferable Unlearnable Examplescited by 4
  17. 2024Beyond Full Poisoning: Effective Availability Attacks with Partial Perturbationcited by 1
  18. 2023Re-thinking Data Availablity Attacks Against Deep Neural Networkscited by 0
  19. 2023Protecting Publicly Available Data With Machine Learning Shortcutscited by 0
  20. 2024Timber! Poisoning Decision Treescited by 0
  21. 2025FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learningcited by 0
  22. 2025Are Targeted Data Poisoning Attacks as Effective as We Think?cited by 0
  23. 2026Reversible Unlearnable Examples: Towards the Copyright Protection in Deep Learning Eracited by 0