mlsanityData to 14 Oct 2026

Robust Trajectory Prediction against Adversarial Attacks

arXiv 2208.00094 ↗First posted 29 Jul 2022cs.LG cs.AI cs.CRcited by 17

Not on the map. Why?

Abstract (arXiv)

Trajectory prediction using deep neural networks (DNNs) is an essential component of autonomous driving (AD) systems. However, these methods are vulnerable to adversarial attacks, leading to serious consequences such as collisions. In this work, we identify two key ingredients to defend trajectory prediction models against adversarial attacks including (1) designing effective adversarial training methods and (2) adding domain-specific data augmentation to mitigate the performance degradation on clean data. We demonstrate that our method is able to improve the performance by 46% on adversarial data and at the cost of only 3% performance degradation on clean data, compared to the model trained with clean data. Additionally, compared to existing robust methods, our method can improve performance by 21% on adversarial examples and 9% on clean data. Our robust model is evaluated with a planner to study its downstream impacts. We demonstrate that our model can significantly reduce the severe accident rates (e.g., collisions and off-road driving).

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 27 of its 39 references that are in the map. First posted on arXiv 29 Jul 2022.

Builds on

27 of 39 references.

References · 27

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  6. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  8. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  9. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  10. 2019Adversarial Training for Free!cited by 643
  11. 2020Overfitting in adversarially robust deep learningcited by 506
  12. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
15 more
  1. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
  2. 2019Adversarial Examples Improve Image Recognitioncited by 286
  3. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 229
  4. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 204
  5. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 179
  6. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Priorcited by 139
  7. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  8. 2022On Adversarial Robustness of Trajectory Prediction for Autonomous Vehiclescited by 90
  9. 2020Smooth Adversarial Trainingcited by 89
  10. 2020Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalizationcited by 73
  11. 2020Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Planscited by 72
  12. 2019ME-Net: Towards Effective Adversarial Robustness with Matrix Estimationcited by 65
  13. 2021Adversarial Attacks On Multi-Agent Communicationcited by 49
  14. 2020A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuningcited by 30
  15. 2017Extending Defensive Distillationcited by 23

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 6; 2025: 3; 2026: 2.

17 papers.

Sort:

By area:

  1. 2023Defending against Adversarial Audio via Diffusion Modelcited by 23
  2. 2023Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?cited by 22
  3. 2024Learning to Drive via Asymmetric Self-Playcited by 11
  4. 2023Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulationcited by 10
  5. 2024Joint Pedestrian Trajectory Prediction through Posterior Samplingcited by 10
  6. 2023TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Modelscited by 8
  7. 2025From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarioscited by 8
  8. 2024Certified Human Trajectory Predictioncited by 6
  9. 2023Improving Autonomous Driving Safety with POP: A Framework for Accurate Partially Observed Trajectory Predictionscited by 5
  10. 2023Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representationscited by 4
  11. 2025Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Drivingcited by 4
  12. 2024A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous Drivingcited by 3
5 more
  1. 2024TrafficGamer: Reliable and Flexible Traffic Simulation for Safety-Critical Scenarios with Game-Theoretic Oraclescited by 1
  2. 2025Adversarial Examples in Environment Perception for Automated Driving (Review)cited by 1
  3. 2026Evaluating randomized smoothing as a defense against adversarial attacks in trajectory predictioncited by 1
  4. 2024Hacking Predictors Means Hacking Cars: Using Sensitivity Analysis to Identify Trajectory Prediction Vulnerabilities for Autonomous Driving Securitycited by 0
  5. 2026RRISE: Robust Radius Inference via a Surrogate Estimatorcited by 0