mlsanityData to 13 Oct 2026

Transferable Unlearnable Examples

arXiv 2210.10114 ↗First posted 18 Oct 2022cs.LG cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

With more people publishing their personal data online, unauthorized data usage has become a serious concern. The unlearnable strategies have been introduced to prevent third parties from training on the data without permission. They add perturbations to the users' data before publishing, which aims to make the models trained on the perturbed published dataset invalidated. These perturbations have been generated for a specific training setting and a target dataset. However, their unlearnable effects significantly decrease when used in other training settings and datasets. To tackle this issue, we propose a novel unlearnable strategy based on Classwise Separability Discriminant (CSD), which aims to better transfer the unlearnable effects to other training settings and datasets by enhancing the linear separability. Extensive experiments demonstrate the transferability of the proposed unlearnable examples across training settings and datasets.

Key facts. Cited by 43 papers in the map (data through 13 Oct 2026). Builds on 12 of its 19 references that are in the map. First posted on arXiv 18 Oct 2022.

Builds on

12 of 19 references.

References · 12

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,379
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,730
  4. 2020Exploring Simple Siamese Representation Learningcited by 2,860
  5. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,285
  6. 2020Shortcut Learning in Deep Neural Networkscited by 1,944
  7. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,397
  8. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 624
  9. 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 196
  10. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 192
  11. 2021Adversarial Examples Make Strong Poisonscited by 119
  12. 2022Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learningcited by 34

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 1; 2023: 10; 2024: 16; 2025: 6; 2026: 10.

43 papers.

Sort:

By area:

  1. 2023MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learningcited by 42
  2. 2023Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compressioncited by 39
  3. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 37
  4. 2022Unlearnable Clusters: Towards Label-agnostic Unlearnable Examplescited by 36
  5. 2023Making Harmful Behaviors Unlearnable for Large Language Modelscited by 19
  6. 2024Provably Unlearnable Data Examplescited by 18
  7. 2023Unlearnable Examples Give a False Sense of Security: Piercing through Unexploitable Data with Learnable Examplescited by 17
  8. 2024Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Needcited by 16
  9. 2024UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentationcited by 14
  10. 2024Semantic Deep Hiding for Robust Unlearnable Examplescited by 13
  11. 2024Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneouslycited by 12
  12. 2023Sharpness-Aware Data Poisoning Attackcited by 10
31 more
  1. 2024Ungeneralizable Examplescited by 9
  2. 2024ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purificationcited by 9
  3. 2024Medical Unlearnable Examples: Securing Medical Data from Unauthorized Training via Sparsity-Aware Local Maskingcited by 8
  4. 2023APBench: A Unified Benchmark for Availability Poisoning Attacks and Defensescited by 7
  5. 2024Toward Availability Attacks in 3D Point Cloudscited by 7
  6. 2023Segue: Side-information Guided Generative Unlearnable Examples for Facial Privacy Protection in Real Worldcited by 6
  7. 2024PID: Prompt-Independent Data Protection Against Latent Diffusion Modelscited by 6
  8. 2023Transferable Availability Poisoning Attackscited by 5
  9. 2024Unlearnable Examples For Time Seriescited by 5
  10. 2025A Survey on Unlearnable Datacited by 5
  11. 2026When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretrainingcited by 5
  12. 2024Towards Operationalizing Right to Data Protectioncited by 3
  13. 2024BridgePure: Limited Protection Leakage Can Break Black-Box Data Protectioncited by 3
  14. 2024ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitationcited by 3
  15. 2025CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarkingcited by 3
  16. 2025T2UE: Generating Unlearnable Examples from Text Descriptionscited by 3
  17. 2026Full spectrum Unlearnable Examples via Spectral Equalizationcited by 3
  18. 2025Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Modelscited by 2
  19. 2025Provable Watermarking for Data Poisoning Attackscited by 2
  20. 2026Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Informationcited by 2
  21. 2026To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Modelcited by 2
  22. 2023Unlearnable Examples Give a False Sense of Data Privacy: Understanding and Relearningcited by 1
  23. 2026Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecyclecited by 1
  24. 2023DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Modelscited by 0
  25. 2024Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspectivecited by 0
  26. 2025Learning to Generate Cross-Task Unexploitable Examplescited by 0
  27. 2026Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Trainingcited by 0
  28. 2026Unlearnable Faces: Privacy Protection Surviving Extraction Pipelinecited by 0
  29. 2026DiffUE: Enhancing Utility-Unlearnability Trade-off of Unlearnable Examples via Diffusion Autoencoderscited by 0
  30. 2026TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Textcited by 0
  31. 2026Reversible Unlearnable Examples: Towards the Copyright Protection in Deep Learning Eracited by 0