mlsanityData to 7 Oct 2026

Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patterns

arXiv 2109.07723 ↗First posted 16 Sep 2021cs.LG cs.AIcited by 13

On the map: End-to-end autonomous driving → Adversarial scenarios and safety testing

Abstract (arXiv)

Recent studies demonstrated the vulnerability of control policies learned through deep reinforcement learning against adversarial attacks, raising concerns about the application of such models to risk-sensitive tasks such as autonomous driving. Threat models for these demonstrations are limited to (1) targeted attacks through real-time manipulation of the agent's observation, and (2) untargeted attacks through manipulation of the physical environment. The former assumes full access to the agent's states/observations at all times, while the latter has no control over attack outcomes. This paper investigates the feasibility of targeted attacks through visually learned patterns placed on physical objects in the environment, a threat model that combines the practicality and effectiveness of the existing ones. Through analysis, we demonstrate that a pre-trained policy can be hijacked within a time window, e.g., performing an unintended self-parking, when an adversarial object is present. To enable the attack, we adopt an assumption that the dynamics of both the environment and the agent can be learned by the attacker. Lastly, we empirically show the effectiveness of the proposed attack on different driving scenarios, perform a location robustness test, and study the tradeoff between the attack strength and its effectiveness. Code is available at https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Placed in Adversarial scenarios and safety testing, one of 9 directions in End-to-end autonomous driving. Builds on 30 of its 38 references that are in the map. First posted on arXiv 16 Sep 2021.

Builds on

30 of 38 references.

References · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  5. 2016Adversarial examples in the physical worldcited by 1,762
  6. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  7. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  8. 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
  9. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  10. 2017One pixel attack for fooling deep neural networkscited by 579
  11. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  12. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
18 more
  1. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 361
  2. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
  3. 2017Adversarial Attacks on Neural Network Policiescited by 314
  4. 2020Agent57: Outperforming the Atari Human Benchmarkcited by 300
  5. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 235
  6. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 231
  7. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  8. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 163
  9. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
  10. 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 123
  11. 2017Delving into adversarial attacks on deep policiescited by 104
  12. 2018CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-drivingcited by 96
  13. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  14. 2019PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Drivingcited by 72
  15. 2020Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learningcited by 62
  16. 2018Deep Reinforcement Learning for Autonomous Drivingcited by 36
  17. 2019Attacking Vision-based Perception in End-to-End Autonomous Driving Modelscited by 31
  18. 2020Finding Physical Adversarial Examples for Autonomous Driving with Fast and Differentiable Image Compositingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 5; 2025: 3; 2026: 1.

13 papers.

Sort:

By area:

  1. 2024RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviorscited by 16
  2. 2024Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learningcited by 5
  3. 2023SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learningcited by 3
  4. 2023Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policycited by 3
  5. 2023Generating Transferable Adversarial Simulation Scenarios for Self-Driving via Neural Renderingcited by 3
  6. 2024Robust Deep Reinforcement Learning against Adversarial Behavior Manipulationcited by 2
  7. 2025Sharpening the Spear: Adaptive Expert-Guided Adversarial Attack Against DRL-based Autonomous Driving Policiescited by 2
  8. 2022Security of Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 1
  9. 2025Robust Driving Control for Autonomous Vehicles: An Intelligent General-sum Constrained Adversarial Reinforcement Learning Approachcited by 1
  10. 2024AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptationcited by 0
  11. 2024Searching Realistic-Looking Adversarial Objects For Autonomous Driving Systemscited by 0
  12. 2025Towards Robust Deep Reinforcement Learning against Environmental State Perturbationcited by 0
1 more
  1. 2026Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Drivingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies
  2. 2021Learning Image Attacks toward Vision Guided Autonomous Vehicles
  3. 2022Don't Watch Me: A Spatio-Temporal Trojan Attack on Deep-Reinforcement-Learning-Augment Autonomous Driving
  4. 2021Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehicles
  5. 2021Adversarial Driving: Attacking End-to-End Autonomous Driving
  6. 2024Visual Adversarial Attack on Vision-Language Models for Autonomous Driving
  7. 2024Attack End-to-End Autonomous Driving through Module-Wise Noise
  8. 2026AD2: Analysis and Detection of Adversarial Threats in Visual Perception for End-to-End Autonomous Driving Systems