mlsanityData to 7 Oct 2026

Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey

arXiv 2105.06300 ↗First posted 13 May 2021cs.CR cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Deep Neural Network (DNN), one of the most powerful machine learning algorithms, is increasingly leveraged to overcome the bottleneck of effectively exploring and analyzing massive data to boost advanced scientific development. It is not a surprise that cloud computing providers offer the cloud-based DNN as an out-of-the-box service. Though there are some benefits from the cloud-based DNN, the interaction mechanism among two or multiple entities in the cloud inevitably induces new privacy risks. This survey presents the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services. We systematically and thoroughly review privacy attacks and defenses in the pipeline of cloud-based DNN service, i.e., data manipulation, training, and prediction. In particular, a new theory, called cloud-based ML privacy game, is extracted from the recently published literature to provide a deep understanding of state-of-the-art research. Finally, the challenges and future work are presented to help researchers to continue to push forward the competitions between privacy attackers and defenders.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 60 of its 143 references that are in the map. First posted on arXiv 13 May 2021.

Builds on

60 of 143 references.

References · 60

  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. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  7. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  10. 2016Deep Learning with Differential Privacycited by 2,682
  11. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  12. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
38 more
  1. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  2. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  3. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
  4. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  5. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  6. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  7. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  8. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  9. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  10. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 449
  11. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  12. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  13. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  14. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  15. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 285
  16. 2016Adversarially Learned Inferencecited by 216
  17. 2019High Accuracy and High Fidelity Extraction of Neural Networkscited by 208
  18. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 183
  19. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  20. 2017Machine Learning Models that Remember Too Muchcited by 165
  21. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 159
  22. 2020Entangled Watermarks as a Defense against Model Extractioncited by 144
  23. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 136
  24. 2013Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifierscited by 128
  25. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117
  26. 2018Stealing Hyperparameters in Machine Learningcited by 115
  27. 2019Analyzing and Improving Representations with the Soft Nearest Neighbor Losscited by 95
  28. 2019DAWN: Dynamic Adversarial Watermarking of Neural Networkscited by 94
  29. 2015A Primer on Neural Network Models for Natural Language Processingcited by 75
  30. 2018Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applicationscited by 67
  31. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 63
  32. 2018AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learningcited by 58
  33. 2018On the Suitability of Lp-norms for Creating and Preventing Adversarial Examplescited by 57
  34. 2021Property Inference From Poisoningcited by 56
  35. 2018Blind Justice: Fairness with Encrypted Sensitive Attributescited by 41
  36. 2019QUOTIENT: Two-Party Secure Neural Network Training and Predictioncited by 41
  37. 2018Digital Watermarking for Deep Neural Networkscited by 37
  38. 2016You are Who You Know and How You Behave: Attribute Inference Attacks via Users' Social Friends and Behaviorscited by 34

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 3.

4 papers.

  1. 2023Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systemscited by 6
  2. 2026Variational Feature Compression for Model-Specific Representationscited by 0
  3. 2026Fair Finetuning Mitigates Distribution Inference Attackscited by 0
  4. 2026Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inferencecited by 0