mlsanityData to 14 Oct 2026

Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review

arXiv 2306.00687 ↗First posted 1 Jun 2023cs.LG cs.CRcited by 3

Not on the map. Why?

Abstract (arXiv)

As the adoption of machine learning models increases, ensuring robust models against adversarial attacks is increasingly important. With unsupervised machine learning gaining more attention, ensuring it is robust against attacks is vital. This paper conducts a systematic literature review on the robustness of unsupervised learning, collecting 86 papers. Our results show that most research focuses on privacy attacks, which have effective defenses; however, many attacks lack effective and general defensive measures. Based on the results, we formulate a model on the properties of an attack on unsupervised learning, contributing to future research by providing a model to use.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 81 of its 163 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

81 of 163 references.

References · 81

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2016Deep Learning with Differential Privacycited by 2,728
  5. 2019An Introduction to Variational Autoencoderscited by 1,000
  6. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  7. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  8. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  9. 2017Generative Adversarial Networks: An Overviewcited by 590
  10. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  11. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  12. 2015Unsupervised Learning of Video Representations using LSTMscited by 435
38 more
  1. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 348
  2. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  3. 2018Differentially Private Generative Adversarial Networkcited by 235
  4. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 197
  5. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 186
  6. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 165
  7. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  8. 2019Reconstruction and Membership Inference Attacks against Generative Modelscited by 122
  9. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117
  10. 2016Towards the Science of Security and Privacy in Machine Learningcited by 89
  11. 2019A Deep Journey into Super-resolution: A surveycited by 86
  12. 2016Defensive Distillation is Not Robust to Adversarial Examplescited by 60
  13. 2018AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learningcited by 60
  14. 2017Adversarial examples for generative modelscited by 58
  15. 2020Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generationcited by 58
  16. 2019G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminatorscited by 53
  17. 2020Differentially Private Synthetic Medical Data Generation using Convolutional GANscited by 52
  18. 2017Defense against Universal Adversarial Perturbationscited by 48
  19. 2019Evaluating Robustness of Deep Image Super-Resolution against Adversarial Attackscited by 37
  20. 2017Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learningcited by 34
  21. 2019PPGAN: Privacy-preserving Generative Adversarial Networkcited by 34
  22. 2020This Face Does Not Exist ... But It Might Be Yours! Identity Leakage in Generative Modelscited by 33
  23. 2021Property Inference Attacks Against GANscited by 33
  24. 2019Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Datacited by 31
  25. 2019A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learningcited by 31
  26. 2017A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analyticscited by 30
  27. 2018Performing Co-Membership Attacks Against Deep Generative Modelscited by 26
  28. 2020BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Modelscited by 25
  29. 2017Regularizing deep networks using efficient layerwise adversarial trainingcited by 24
  30. 2021Adversarial Attacks Against Deep Generative Models on Data: A Surveycited by 24
  31. 2021FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumoniacited by 22
  32. 2017Robustness to Adversarial Examples through an Ensemble of Specialistscited by 21
  33. 2016Adversarial Images for Variational Autoencoderscited by 19
  34. 2017Blocking Transferability of Adversarial Examples in Black-Box Learning Systemscited by 19
  35. 2018Adversarial Attacks on Variational Autoencoderscited by 19
  36. 2018Security and Privacy Issues in Deep Learningcited by 19
  37. 2019Physical Adversarial Attacks Against End-to-End Autoencoder Communication Systemscited by 19
  38. 2018Is Data Clustering in Adversarial Settings Secure?cited by 18

50 most cited of 81 All 81 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024Adaptive Anomaly Detection for Identifying Attacks in Cyber-Physical Systems: A Systematic Literature Reviewcited by 2
  2. 2024Assessing Robustness of Machine Learning Models using Covariate Perturbationscited by 1
  3. 2024LaFA: Latent Feature Attacks on Non-negative Matrix Factorizationcited by 0