mlsanityData to 7 Oct 2026

Evaluating Automated Driving Planner Robustness against Adversarial Influence

arXiv 2205.14697 ↗First posted 29 May 2022cs.CR cs.AI cs.LGcited by 0

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

Abstract (arXiv)

Evaluating the robustness of automated driving planners is a critical and challenging task. Although methodologies to evaluate vehicles are well established, they do not yet account for a reality in which vehicles with autonomous components share the road with adversarial agents. Our approach, based on probabilistic trust models, aims to help researchers assess the robustness of protections for machine learning-enabled planners against adversarial influence. In contrast with established practices that evaluate safety using the same evaluation dataset for all vehicles, we argue that adversarial evaluation fundamentally requires a process that seeks to defeat a specific protection. Hence, we propose that evaluations be based on estimating the difficulty for an adversary to determine conditions that effectively induce unsafe behavior. This type of inference requires precise statements about threats, protections, and aspects of planning decisions to be guarded. We demonstrate our approach by evaluating protections for planners relying on camera-based object detectors.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Adversarial scenarios and safety testing, one of 9 directions in End-to-end autonomous driving. Builds on 14 of its 21 references that are in the map. First posted on arXiv 29 May 2022.

Builds on

14 of 21 references.

References · 14

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2018YOLOv3: An Incremental Improvementcited by 2,652
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  5. 2017Adversarial Patchcited by 514
  6. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  7. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  8. 2020A Survey of Algorithms for Black-Box Safety Validation of Cyber-Physical Systemscited by 71
  9. 2021Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)cited by 40
  10. 2019APRICOT: A Dataset of Physical Adversarial Attacks on Object Detectioncited by 30
  11. 2018Simulation-based Adversarial Test Generation for Autonomous Vehicles with Machine Learning Componentscited by 28
  12. 2019Bayesian Optimization for Categorical and Category-Specific Continuous Inputscited by 28
2 more
  1. 2019Efficient Black-box Assessment of Autonomous Vehicle Safetycited by 23
  2. 2018Autonomous Vehicle: Security by Designcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Real-Time Evaluation of Autonomous Systems under Adversarial Attacks
  2. 2026Learning Responsibility-Attributed Adversarial Scenarios for Testing Autonomous Vehicles
  3. 2025Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions
  4. 2024Training Adversarial yet Safe Agent to Characterize Safety Performance of Highly Automated Vehicles
  5. 2025Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems
  6. 2021On Robustness of Lane Detection Models to Physical-World Adversarial Attacks in Autonomous Driving
  7. 2021Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehicles
  8. 2023SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries