mlsanityData to 7 Oct 2026

Privacy in Deep Learning: A Survey

arXiv 2004.12254 ↗First posted 25 Apr 2020cs.LG cs.CR stat.MLcited by 70

Not on the map. Why?

Abstract (arXiv)

The ever-growing advances of deep learning in many areas including vision, recommendation systems, natural language processing, etc., have led to the adoption of Deep Neural Networks (DNNs) in production systems. The availability of large datasets and high computational power are the main contributors to these advances. The datasets are usually crowdsourced and may contain sensitive information. This poses serious privacy concerns as this data can be misused or leaked through various vulnerabilities. Even if the cloud provider and the communication link is trusted, there are still threats of inference attacks where an attacker could speculate properties of the data used for training, or find the underlying model architecture and parameters. In this survey, we review the privacy concerns brought by deep learning, and the mitigating techniques introduced to tackle these issues. We also show that there is a gap in the literature regarding test-time inference privacy, and propose possible future research directions.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 15; 2023: 12; 2024: 17; 2025: 5; 2026: 2.

70 papers.

Sort:

By area:

  1. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  2. 2023Large Language Model Alignment: A Surveycited by 241
  3. 2022Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attackscited by 168
  4. 2021Federated Learning for Open Bankingcited by 138
  5. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  6. 2024Towards Modular LLMs by Building and Reusing a Library of LoRAscited by 72
  7. 2024Clio: Privacy-Preserving Insights into Real-World AI Usecited by 66
  8. 2021Socially Responsible AI Algorithms: Issues, Purposes, and Challengescited by 56
  9. 2023FedMultimodal: A Benchmark For Multimodal Federated Learningcited by 51
  10. 2024MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Modelscited by 51
  11. 2022Memorization in NLP Fine-tuning Methodscited by 43
  12. 2021Membership Inference on Word Embedding and Beyondcited by 34
38 more
  1. 2021DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?cited by 32
  2. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  3. 2021Privacy Regularization: Joint Privacy-Utility Optimization in Language Modelscited by 29
  4. 2021UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysiscited by 28
  5. 2023A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applicationscited by 22
  6. 2021Collaborative Intelligence: Challenges and Opportunitiescited by 18
  7. 2021Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputscited by 18
  8. 2024Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutionscited by 15
  9. 2022Differentially Private Model Compressioncited by 13
  10. 2022DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardwarecited by 13
  11. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  12. 2021Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settingscited by 12
  13. 2023Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Surveycited by 12
  14. 2022Binarizing Split Learning for Data Privacy Enhancement and Computation Reductioncited by 11
  15. 2023Unsupervised Deep Learning for IoT Time Seriescited by 11
  16. 2021Interference Suppression Using Deep Learning: Current Approaches and Open Challengescited by 10
  17. 2022Privacy Leakage in Text Classification: A Data Extraction Approachcited by 9
  18. 2021When Differential Privacy Meets Interpretability: A Case Studycited by 8
  19. 2024A General Framework for Learning from Weak Supervisioncited by 7
  20. 2022Federated Domain Adaptation for ASR with Full Self-Supervisioncited by 6
  21. 2023Hierarchical Training of Deep Neural Networks Using Early Exitingcited by 5
  22. 2024The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Modelscited by 5
  23. 2021Confidential Machine Learning Computation in Untrusted Environments: A Systems Security Perspectivecited by 4
  24. 2023Quantifying Overfitting: Evaluating Neural Network Performance through Analysis of Null Spacecited by 4
  25. 2025Cellular Traffic Prediction via Byzantine-robust Asynchronous Federated Learningcited by 4
  26. 2021MPCLeague: Robust MPC Platform for Privacy-Preserving Machine Learningcited by 3
  27. 2023Data Encoding For Healthcare Data Democratisation and Information Leakage Preventioncited by 3
  28. 2024A Survey on Privacy Attacks Against Digital Twin Systems in AI-Roboticscited by 3
  29. 2024Sharper Bounds for Chebyshev Moment Matching, with Applicationscited by 3
  30. 2021Privacy-Preserving Image Acquisition Using Trainable Optical Kernelcited by 2
  31. 2022Securing the Classification of COVID-19 in Chest X-ray Images: A Privacy-Preserving Deep Learning Approachcited by 2
  32. 2022Privacy-Preserving Feature Coding for Machinescited by 2
  33. 2023A Comprehensive Study of Privacy Risks in Curriculum Learningcited by 2
  34. 2024EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registrationcited by 2
  35. 2024Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognitioncited by 2
  36. 2021On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Modelscited by 1
  37. 2021Addressing Privacy Threats from Machine Learningcited by 1
  38. 2022Memorization of Named Entities in Fine-tuned BERT Modelscited by 1

50 most cited of 70 All 70 (JSON)