mlsanityData to 7 Oct 2026

On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles

arXiv 2201.05057 ↗First posted 13 Jan 2022cs.CV cs.CRcited by 89

Not on the map. Why?

Abstract (arXiv)

Trajectory prediction is a critical component for autonomous vehicles (AVs) to perform safe planning and navigation. However, few studies have analyzed the adversarial robustness of trajectory prediction or investigated whether the worst-case prediction can still lead to safe planning. To bridge this gap, we study the adversarial robustness of trajectory prediction models by proposing a new adversarial attack that perturbs normal vehicle trajectories to maximize the prediction error. Our experiments on three models and three datasets show that the adversarial prediction increases the prediction error by more than 150%. Our case studies show that if an adversary drives a vehicle close to the target AV following the adversarial trajectory, the AV may make an inaccurate prediction and even make unsafe driving decisions. We also explore possible mitigation techniques via data augmentation and trajectory smoothing. The implementation is open source at https://github.com/zqzqz/AdvTrajectoryPrediction.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). Builds on 28 of its 41 references that are in the map. First posted on arXiv 13 Jan 2022.

Builds on

28 of 41 references.

References · 28

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  4. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  5. 2019On Evaluating Adversarial Robustnesscited by 442
  6. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  7. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 324
  8. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  9. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 151
  10. 2021AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehiclescited by 132
  11. 2020LGSVL Simulator: A High Fidelity Simulator for Autonomous Drivingcited by 119
  12. 2018TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agentscited by 111
16 more
  1. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  2. 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
  3. 2018TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactionscited by 82
  4. 2020Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Planscited by 72
  5. 2020MANTRA: Memory Augmented Networks for Multiple Trajectory Predictioncited by 69
  6. 2020Recursive Social Behavior Graph for Trajectory Predictioncited by 66
  7. 2020Dirty Road Can Attack: Security of Deep Learning based Automated Lane Centering under Physical-World Attackcited by 64
  8. 2021When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarkscited by 41
  9. 2021Divide-and-Conquer for Lane-Aware Diverse Trajectory Predictioncited by 37
  10. 2019Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMscited by 34
  11. 2021Are socially-aware trajectory prediction models really socially-aware?cited by 32
  12. 2020Shared Cross-Modal Trajectory Prediction for Autonomous Drivingcited by 31
  13. 2020Reciprocal Learning Networks for Human Trajectory Predictioncited by 30
  14. 2019RobustTP: End-to-End Trajectory Prediction for Heterogeneous Road-Agents in Dense Traffic with Noisy Sensor Inputscited by 16
  15. 2020Multi-agent Trajectory Prediction with Fuzzy Query Attentioncited by 16
  16. 2019Fooling Detection Alone is Not Enough: First Adversarial Attack against Multiple Object Trackingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 24; 2024: 23; 2025: 17; 2026: 15.

89 papers.

Sort:

By area:

  1. 2024ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehiclescited by 92
  2. 2022SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehiclescited by 65
  3. 2023CAT: Closed-loop Adversarial Training for Safe End-to-End Drivingcited by 52
  4. 2022AdvDO: Realistic Adversarial Attacks for Trajectory Predictioncited by 48
  5. 2023Synthetic Datasets for Autonomous Driving: A Surveycited by 48
  6. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  7. 2023ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformercited by 43
  8. 2023SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversariescited by 36
  9. 2022Behavioral Intention Prediction in Driving Scenes: A Surveycited by 30
  10. 2024AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusioncited by 20
  11. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  12. 2022CausalAgents: A Robustness Benchmark for Motion Forecasting using Causal Relationshipscited by 18
38 more
  1. 2023RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understandingcited by 17
  2. 2023Joint Metrics Matter: A Better Standard for Trajectory Forecastingcited by 17
  3. 2022Robust Trajectory Prediction against Adversarial Attackscited by 16
  4. 2022PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognitioncited by 16
  5. 2024Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving Priorscited by 15
  6. 2023CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perceptioncited by 14
  7. 2024Traffic Scene Generation from Natural Language Description for Autonomous Vehicles with Large Language Modelcited by 14
  8. 2022Semi-supervised Semantics-guided Adversarial Training for Trajectory Predictioncited by 12
  9. 2022Targeted Adversarial Attacks against Neural Network Trajectory Predictorscited by 11
  10. 2023Physics Constrained Motion Prediction with Uncertainty Quantificationcited by 11
  11. 2023Fusion is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detectioncited by 11
  12. 2023On Data Fabrication in Collaborative Vehicular Perception: Attacks and Countermeasurescited by 11
  13. 2023VPA: Fully Test-Time Visual Prompt Adaptationcited by 11
  14. 2024Learning to Drive via Asymmetric Self-Playcited by 11
  15. 2022Towards Explainable Motion Prediction using Heterogeneous Graph Representationscited by 10
  16. 2023Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulationcited by 10
  17. 2025LD-Scene: LLM-Guided Diffusion for Controllable Generation of Adversarial Safety-Critical Driving Scenarioscited by 9
  18. 2023TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Modelscited by 8
  19. 2024Enhancing Adversarial Robustness of Vision-Language Models through Low-Rank Adaptationcited by 8
  20. 2025PlanT 2.0: Exposing Biases and Structural Flaws in Closed-Loop Drivingcited by 8
  21. 2025DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Modelscited by 7
  22. 2023Learning Representation for Anomaly Detection of Vehicle Trajectoriescited by 6
  23. 2024Certified Human Trajectory Predictioncited by 6
  24. 2024Enhancing LLM-based Autonomous Driving Agents to Mitigate Perception Attackscited by 6
  25. 2022Benchmark for Models Predicting Human Behavior in Gap Acceptance Scenarioscited by 5
  26. 2023Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Drivingcited by 5
  27. 2023Improving Autonomous Driving Safety with POP: A Framework for Accurate Partially Observed Trajectory Predictionscited by 5
  28. 2023Indirect Gradient Matching for Adversarial Robust Distillationcited by 5
  29. 2024Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learningcited by 5
  30. 2025Long-tailed Adversarial Training with Self-Distillationcited by 5
  31. 2025AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Frameworkcited by 5
  32. 2023Privacy-preserving and Uncertainty-aware Federated Trajectory Prediction for Connected Autonomous Vehiclescited by 4
  33. 2024Decictor: Towards Evaluating the Robustness of Decision-Making in Autonomous Driving Systemscited by 4
  34. 2024Module-wise Adaptive Adversarial Training for End-to-end Autonomous Drivingcited by 4
  35. 2025Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehiclescited by 4
  36. 2024A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous Drivingcited by 3
  37. 2024Evaluating Human Trajectory Prediction with Metamorphic Testingcited by 3
  38. 2024Privacy-preserving Universal Adversarial Defense for Black-box Modelscited by 3

50 most cited of 89 All 89 (JSON)