mlsanityData to 7 Oct 2026

ARC: Adversarially Robust Control Policies for Autonomous Vehicles

arXiv 2107.04487 ↗First posted 9 Jul 2021cs.LG cs.AI cs.MAcited by 3

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

Abstract (arXiv)

Deep neural networks have demonstrated their capability to learn control policies for a variety of tasks. However, these neural network-based policies have been shown to be susceptible to exploitation by adversarial agents. Therefore, there is a need to develop techniques to learn control policies that are robust against adversaries. We introduce Adversarially Robust Control (ARC), which trains the protagonist policy and the adversarial policy end-to-end on the same loss. The aim of the protagonist is to maximise this loss, whilst the adversary is attempting to minimise it. We demonstrate the proposed ARC training in a highway driving scenario, where the protagonist controls the follower vehicle whilst the adversary controls the lead vehicle. By training the protagonist against an ensemble of adversaries, it learns a significantly more robust control policy, which generalises to a variety of adversarial strategies. The approach is shown to reduce the amount of collisions against new adversaries by up to 90.25%, compared to the original policy. Moreover, by utilising an auxiliary distillation loss, we show that the fine-tuned control policy shows no drop in performance across its original training distribution.

Key facts. Cited by 3 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 33 of its 51 references that are in the map. First posted on arXiv 9 Jul 2021.

Builds on

33 of 51 references.

References · 33

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Learning without Forgettingcited by 2,465
  5. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  6. 2016Generative Adversarial Imitation Learningcited by 1,576
  7. 2018World Modelscited by 1,444
  8. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  9. 2016End to End Learning for Self-Driving Carscited by 1,000
  10. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  11. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 711
  12. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
21 more
  1. 2017Robust Adversarial Reinforcement Learningcited by 439
  2. 2015Policy Distillationcited by 414
  3. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  4. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  5. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
  6. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  7. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  8. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
  9. 2019A Survey of Deep Learning Applications to Autonomous Vehicle Controlcited by 101
  10. 2017Imitating Driver Behavior with Generative Adversarial Networkscited by 92
  11. 2016Sim-to-Real Robot Learning from Pixels with Progressive Netscited by 89
  12. 2017Virtual to Real Reinforcement Learning for Autonomous Drivingcited by 79
  13. 2020A Survey of Algorithms for Black-Box Safety Validation of Cyber-Physical Systemscited by 71
  14. 2019Adaptive Stress Testing for Autonomous Vehiclescited by 70
  15. 2019Risk Averse Robust Adversarial Reinforcement Learningcited by 54
  16. 2020Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluationcited by 54
  17. 2019Simulation-based reinforcement learning for real-world autonomous drivingcited by 51
  18. 2017Less-forgetful Learning for Domain Expansion in Deep Neural Networkscited by 27
  19. 2020Training Adversarial Agents to Exploit Weaknesses in Deep Control Policiescited by 24
  20. 2019Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learningcited by 23
  21. 2018Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehiclescited by 8

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 2.

3 papers.

  1. 2022Reducing Exploitability with Population Based Trainingcited by 4
  2. 2025Offline Reinforcement Learning using Human-Aligned Reward Labeling for Autonomous Emergency Braking in Occluded Pedestrian Crossingcited by 1
  3. 2025DiffFP: Learning Behaviors from Scratch via Diffusion-based Fictitious Playcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Robust Driving Control for Autonomous Vehicles: An Intelligent General-sum Constrained Adversarial Reinforcement Learning Approach
  2. 2021Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies
  3. 2026From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving
  4. 2024VCAT: Vulnerability-aware and Curiosity-driven Adversarial Training for Enhancing Autonomous Vehicle Robustness
  5. 2026ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving
  6. 2026Real-Time Evaluation of Autonomous Systems under Adversarial Attacks
  7. 2024Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving
  8. 2026Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving