mlsanityData to 7 Oct 2026

Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses

arXiv 2104.01789 ↗First posted 5 Apr 2021cs.LG cs.CR cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

The rapid development of artificial intelligence, especially deep learning technology, has advanced autonomous driving systems (ADSs) by providing precise control decisions to counterpart almost any driving event, spanning from anti-fatigue safe driving to intelligent route planning. However, ADSs are still plagued by increasing threats from different attacks, which could be categorized into physical attacks, cyberattacks and learning-based adversarial attacks. Inevitably, the safety and security of deep learning-based autonomous driving are severely challenged by these attacks, from which the countermeasures should be analyzed and studied comprehensively to mitigate all potential risks. This survey provides a thorough analysis of different attacks that may jeopardize ADSs, as well as the corresponding state-of-the-art defense mechanisms. The analysis is unrolled by taking an in-depth overview of each step in the ADS workflow, covering adversarial attacks for various deep learning models and attacks in both physical and cyber context. Furthermore, some promising research directions are suggested in order to improve deep learning-based autonomous driving safety, including model robustness training, model testing and verification, and anomaly detection based on cloud/edge servers.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 72 of its 127 references that are in the map. First posted on arXiv 5 Apr 2021.

Builds on

72 of 127 references.

References · 72

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2015Fast R-CNNcited by 2,930
  8. 2016Pyramid Scene Parsing Networkcited by 2,472
  9. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  10. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  11. 2016Adversarial examples in the physical worldcited by 1,762
  12. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
38 more
  1. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  2. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  3. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  4. 2016End to End Learning for Self-Driving Carscited by 1,000
  5. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  6. 2016Adversarial Machine Learning at Scalecited by 934
  7. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  8. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  9. 2016Universal adversarial perturbationscited by 774
  10. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  11. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  12. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  13. 2017One pixel attack for fooling deep neural networkscited by 579
  14. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  15. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  16. 2017Countering Adversarial Images using Input Transformationscited by 517
  17. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  18. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  19. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  20. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  21. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  22. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 437
  23. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  24. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  25. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  26. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  27. 2017Adversarial Attacks on Neural Network Policiescited by 314
  28. 2018Certified Defenses against Adversarial Examplescited by 305
  29. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  30. 2016Safety Verification of Deep Neural Networkscited by 262
  31. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  32. 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
  33. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  34. 2017DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networkscited by 173
  35. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 163
  36. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  37. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  38. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 8; 2024: 4; 2025: 5; 2026: 6.

29 papers.

Sort:

By area:

  1. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
  2. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 38
  3. 2022Robustness Analysis of Video-Language Models Against Visual and Language Perturbationscited by 23
  4. 2022SoK: On the Semantic AI Security in Autonomous Drivingcited by 22
  5. 2023Deep Learning Safety Concerns in Automated Driving Perceptioncited by 10
  6. 2024TimeLDM: Latent Diffusion Model for Unconditional Time Series Generationcited by 10
  7. 2023Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunitiescited by 9
  8. 2022Partial Connection Based on Channel Attention for Differentiable Neural Architecture Searchcited by 7
  9. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  10. 2025NeuroStrata: Harnessing Neurosymbolic Paradigms for Improved Design, Testability, and Verifiability of Autonomous CPScited by 5
  11. 2024Data Poisoning Attacks in Intelligent Transportation Systems: A Surveycited by 4
  12. 2022Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Surveycited by 3
17 more
  1. 2024Benchmarking Deep Reinforcement Learning for Navigation in Denied Sensor Environmentscited by 3
  2. 2026ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Drivingcited by 3
  3. 2023Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifierscited by 2
  4. 2023An Overview about Emerging Technologies of Autonomous Drivingcited by 2
  5. 2025GPS Spoofing Attack Detection in Autonomous Vehicles Using Adaptive DBSCANcited by 2
  6. 2022Security of Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 1
  7. 2023Detection of Adversarial Physical Attacks in Time-Series Image Datacited by 1
  8. 2025VisMoDAl: Visual Analytics for Evaluating and Improving Corruption Robustness of Vision-Language Modelscited by 1
  9. 2025Advancing Autonomous Driving System Testing: Demands, Challenges, and Future Directionscited by 1
  10. 2023VSRQ: Quantitative Assessment Method for Safety Risk of Vehicle Intelligent Connected Systemcited by 0
  11. 2024A Safety-Oriented Self-Learning Algorithm for Autonomous Driving: Evolution Starting from a Basic Modelcited by 0
  12. 2025DeBUGCN -- Detecting Backdoors in CNNs Using Graph Convolutional Networkscited by 0
  13. 2026Robust Vision Systems for Connected and Autonomous Vehicles: Security Challenges and Attack Vectorscited by 0
  14. 2026UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systemscited by 0
  15. 2026Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Drivingcited by 0
  16. 2026Provable Fairness Repair for Deep Neural Networkscited by 0
  17. 2026Edge Physical AI Deployment of Vision Transformers on Heterogeneous Edge GPU Targeting Autonomous Vehiclescited by 0