mlsanityData to 7 Oct 2026

Privacy of Autonomous Vehicles: Risks, Protection Methods, and Future Directions

arXiv 2209.04022 ↗First posted 8 Sep 2022cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Recent advances in machine learning have enabled its wide application in different domains, and one of the most exciting applications is autonomous vehicles (AVs), which have encouraged the development of a number of ML algorithms from perception to prediction to planning. However, training AVs usually requires a large amount of training data collected from different driving environments (e.g., cities) as well as different types of personal information (e.g., working hours and routes). Such collected large data, treated as the new oil for ML in the data-centric AI era, usually contains a large amount of privacy-sensitive information which is hard to remove or even audit. Although existing privacy protection approaches have achieved certain theoretical and empirical success, there is still a gap when applying them to real-world applications such as autonomous vehicles. For instance, when training AVs, not only can individually identifiable information reveal privacy-sensitive information, but also population-level information such as road construction within a city, and proprietary-level commercial secrets of AVs. Thus, it is critical to revisit the frontier of privacy risks and corresponding protection approaches in AVs to bridge this gap. Following this goal, in this work, we provide a new taxonomy for privacy risks and protection methods in AVs, and we categorize privacy in AVs into three levels: individual, population, and proprietary. We explicitly list out recent challenges to protect each of these levels of privacy, summarize existing solutions to these challenges, discuss the lessons and conclusions, and provide potential future directions and opportunities for both researchers and practitioners. We believe this work will help to shape the privacy research in AV and guide the privacy protection technology design.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 76 of its 211 references that are in the map. First posted on arXiv 8 Sep 2022.

Builds on

76 of 211 references.

References · 76

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2018YOLOv3: An Incremental Improvementcited by 2,652
  7. 2016Pyramid Scene Parsing Networkcited by 2,472
  8. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  9. 2014Conditional Generative Adversarial Netscited by 2,152
  10. 2019Deep Leakage from Gradientscited by 1,004
  11. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  12. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
38 more
  1. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  2. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  3. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
  4. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  5. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  6. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  7. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
  8. 2021Differentially Private Fine-tuning of Language Modelscited by 392
  9. 2020Learning Lane Graph Representations for Motion Forecastingcited by 380
  10. 2020Label-Only Membership Inference Attackscited by 371
  11. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  12. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  13. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  14. 2015WIDER FACE: A Face Detection Benchmarkcited by 297
  15. 2018Scalable Private Learning with PATEcited by 266
  16. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  17. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 237
  18. 2018Differentially Private Generative Adversarial Networkcited by 235
  19. 2019High Accuracy and High Fidelity Extraction of Neural Networkscited by 208
  20. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  21. 2017Machine Learning Models that Remember Too Muchcited by 165
  22. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 159
  23. 2018cpSGD: Communication-efficient and differentially-private distributed SGDcited by 157
  24. 2019Thieves on Sesame Street! Model Extraction of BERT-based APIscited by 136
  25. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  26. 2020DP-CGAN: Differentially Private Synthetic Data and Label Generationcited by 118
  27. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117
  28. 2018Stealing Hyperparameters in Machine Learningcited by 115
  29. 2020Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehiclescited by 101
  30. 2018Baidu Apollo EM Motion Plannercited by 99
  31. 2018Model Reconstruction from Model Explanationscited by 84
  32. 2018Exploring Connections Between Active Learning and Model Extractioncited by 84
  33. 2019Reverse-Engineering Deep ReLU Networkscited by 81
  34. 2018Towards Robust and Privacy-preserving Text Representationscited by 75
  35. 2020Cryptanalytic Extraction of Neural Network Modelscited by 65
  36. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 63
  37. 2017Efficient Private ERM for Smooth Objectivescited by 61
  38. 2018Cache Telepathy: Leveraging Shared Resource Attacks to Learn DNN Architecturescited by 56

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2024AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Drivingcited by 35
  2. 2025Privacy-Preserving in Connected and Autonomous Vehicles Through Vision to Text Transformationcited by 1
  3. 2025I2V-GS: Infrastructure-to-Vehicle View Transformation with Gaussian Splatting for Autonomous Driving Data Generationcited by 0
  4. 2025RL-MoE: An Image-Based Privacy Preserving Approach In Intelligent Transportation Systemcited by 0