Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey
Not on the map. Why?
Abstract (arXiv)
Since the 2004 DARPA Grand Challenge, the autonomous driving technology has witnessed nearly two decades of rapid development. Particularly, in recent years, with the application of new sensors and deep learning technologies extending to the autonomous field, the development of autonomous driving technology has continued to make breakthroughs. Thus, many carmakers and high-tech giants dedicated to research and system development of autonomous driving. However, as the foundation of autonomous driving, the deep learning technology faces many new security risks. The academic community has proposed deep learning countermeasures against the adversarial examples and AI backdoor, and has introduced them into the autonomous driving field for verification. Deep learning security matters to autonomous driving system security, and then matters to personal safety, which is an issue that deserves attention and research.This paper provides an summary of the concepts, developments and recent research in deep learning security technologies in autonomous driving. Firstly, we briefly introduce the deep learning framework and pipeline in the autonomous driving system, which mainly include the deep learning technologies and algorithms commonly used in this field. Moreover, we focus on the potential security threats of the deep learning based autonomous driving system in each functional layer in turn. We reviews the development of deep learning attack technologies to autonomous driving, investigates the State-of-the-Art algorithms, and reveals the potential risks. At last, we provides an outlook on deep learning security in the autonomous driving field and proposes recommendations for building a safe and trustworthy autonomous driving system.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 154 of its 242 references that are in the map. First posted on arXiv 19 Oct 2022.
Builds on
154 of 242 references.
References · 154
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Mask R-CNNcited by 7,259
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2015SSD: Single Shot MultiBox Detectorcited by 3,125
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
38 more
- 2015Fast R-CNNcited by 2,930
- 2018YOLOv3: An Incremental Improvementcited by 2,652
- 2016Pyramid Scene Parsing Networkcited by 2,472
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
- 2016Adversarial examples in the physical worldcited by 1,762
- 2016Generative Adversarial Imitation Learningcited by 1,576
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
- 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
- 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
- 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
- 2016Practical Black-Box Attacks against Machine Learningcited by 893
- 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
- 2016Universal adversarial perturbationscited by 774
- 2018How To Backdoor Federated Learningcited by 745
- 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
- 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
- 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
- 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
- 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
- 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
- 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
- 2016Stealing Machine Learning Models via Prediction APIscited by 602
- 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
- 2022Vision Transformer Adapter for Dense Predictionscited by 564
- 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
- 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
- 2018Object Detection with Deep Learning: A Reviewcited by 524
- 2017Adversarial Patchcited by 514
- 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
- 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
- 2017End-to-end Driving via Conditional Imitation Learningcited by 479
- 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 477
- 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
50 most cited of 154 All 154 (JSON)
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 0; 2026: 1.
3 papers.