mlsanityData to 14 Oct 2026

TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models

arXiv 2308.05985 ↗First posted 11 Aug 2023cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Robust pedestrian trajectory forecasting is crucial to developing safe autonomous vehicles. Although previous works have studied adversarial robustness in the context of trajectory forecasting, some significant issues remain unaddressed. In this work, we try to tackle these crucial problems. Firstly, the previous definitions of robustness in trajectory prediction are ambiguous. We thus provide formal definitions for two kinds of robustness, namely label robustness and pure robustness. Secondly, as previous works fail to consider robustness about all points in a disturbance interval, we utilise a probably approximately correct (PAC) framework for robustness verification. Additionally, this framework can not only identify potential counterexamples, but also provides interpretable analyses of the original methods. Our approach is applied using a prototype tool named TrajPAC. With TrajPAC, we evaluate the robustness of four state-of-the-art trajectory prediction models -- Trajectron++, MemoNet, AgentFormer, and MID -- on trajectories from five scenes of the ETH/UCY dataset and scenes of the Stanford Drone Dataset. Using our framework, we also experimentally study various factors that could influence robustness performance.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 68 of its 102 references that are in the map. First posted on arXiv 11 Aug 2023.

Builds on

68 of 102 references.

References · 68

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  6. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  7. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
  8. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  9. 2019On Evaluating Adversarial Robustnesscited by 447
  10. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 420
  11. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
  12. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 325
38 more
  1. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  2. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 298
  3. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  4. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  5. 2018Generating Adversarial Examples with Adversarial Networkscited by 258
  6. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 236
  7. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 229
  8. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 214
  9. 2017Social Attention: Modeling Attention in Human Crowdscited by 186
  10. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 185
  11. 2019Multiple Futures Predictioncited by 178
  12. 2016Generating Visual Explanationscited by 158
  13. 2018Generating 3D Adversarial Point Cloudscited by 144
  14. 2019Multi-Agent Tensor Fusion for Contextual Trajectory Predictioncited by 131
  15. 2020NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systemscited by 128
  16. 2022GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoningcited by 128
  17. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  18. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  19. 2022On Adversarial Robustness of Trajectory Prediction for Autonomous Vehiclescited by 90
  20. 2022Remember Intentions: Retrospective-Memory-based Trajectory Predictioncited by 86
  21. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  22. 2020TPNet: Trajectory Proposal Network for Motion Predictioncited by 80
  23. 2019Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANscited by 79
  24. 2019Conditional Generative Neural System for Probabilistic Trajectory Predictioncited by 76
  25. 2021Improving Deep Learning Interpretability by Saliency Guided Trainingcited by 68
  26. 2020PatchAttack: A Black-box Texture-based Attack with Reinforcement Learningcited by 67
  27. 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61
  28. 2020Social NCE: Contrastive Learning of Socially-aware Motion Representationscited by 58
  29. 2019Quantitative Verification of Neural Networks And its Security Applicationscited by 56
  30. 2018A Statistical Approach to Assessing Neural Network Robustnesscited by 54
  31. 2020BayLIME: Bayesian Local Interpretable Model-Agnostic Explanationscited by 51
  32. 2018CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networkscited by 50
  33. 2022AdvDO: Realistic Adversarial Attacks for Trajectory Predictioncited by 49
  34. 2021Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesiscited by 46
  35. 2022Non-Probability Sampling Network for Stochastic Human Trajectory Predictioncited by 46
  36. 2020Probabilistic Safety for Bayesian Neural Networkscited by 42
  37. 2022Enhancing Adversarial Training with Second-Order Statistics of Weightscited by 42
  38. 2019Robustness of Neural Networks: A Probabilistic and Practical Approachcited by 38

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 1.

8 papers.

  1. 2025Enhancing Robust Fairness via Confusional Spectral Regularizationcited by 11
  2. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  3. 2024Certified Human Trajectory Predictioncited by 6
  4. 2024Evaluating Human Trajectory Prediction with Metamorphic Testingcited by 3
  5. 2024Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectorscited by 3
  6. 2024RealTraj: Towards Real-World Pedestrian Trajectory Forecastingcited by 3
  7. 2025Shapley Uncertainty in Natural Language Generationcited by 2
  8. 2026TrajRS: Towards Certified Robustness in Pedestrian Trajectory Predictioncited by 0