mlsanityData to 14 Oct 2026

AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusion

arXiv 2410.08453 ↗First posted 11 Oct 2024cs.LG cs.ROcited by 20

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

Safety-critical scenarios are infrequent in natural driving environments but hold significant importance for the training and testing of autonomous driving systems. The prevailing approach involves generating safety-critical scenarios automatically in simulation by introducing adversarial adjustments to natural environments. These adjustments are often tailored to specific tested systems, thereby disregarding their transferability across different systems. In this paper, we propose AdvDiffuser, an adversarial framework for generating safety-critical driving scenarios through guided diffusion. By incorporating a diffusion model to capture plausible collective behaviors of background vehicles and a lightweight guide model to effectively handle adversarial scenarios, AdvDiffuser facilitates transferability. Experimental results on the nuScenes dataset demonstrate that AdvDiffuser, trained on offline driving logs, can be applied to various tested systems with minimal warm-up episode data and outperform other existing methods in terms of realism, diversity, and adversarial performance.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 31 of its 42 references that are in the map. First posted on arXiv 11 Oct 2024.

Builds on

31 of 42 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL31 May
  2. 2022Guided Conditional Diffusion for Controllable Traffic Simulation31 Oct

Other references · 29

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  7. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  8. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  9. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  10. 2015Generating Sentences from a Continuous Spacecited by 612
  11. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 346
  12. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learningcited by 290
17 more
  1. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 213
  2. 2021TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviorscited by 193
  3. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 185
  4. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Priorcited by 139
  5. 2021AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehiclescited by 137
  6. 2019Meta-Sim: Learning to Generate Synthetic Datasetscited by 128
  7. 2022TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarioscited by 106
  8. 2022A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspectivecited by 105
  9. 2022KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradientscited by 96
  10. 2022On Adversarial Robustness of Trajectory Prediction for Autonomous Vehiclescited by 90
  11. 2021SimNet: Learning Reactive Self-driving Simulations from Real-world Observationscited by 77
  12. 2020Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Methodcited by 75
  13. 2023Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveyscited by 75
  14. 2022Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulationcited by 61
  15. 2020Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluationcited by 55
  16. 2023Rethinking Closed-loop Training for Autonomous Drivingcited by 29
  17. 2019CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarioscited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 12; 2026: 7.

20 papers.

Sort:

By area:

  1. 2025Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysiscited by 38
  2. 2024Causal Composition Diffusion Model for Closed-loop Traffic Generationcited by 22
  3. 2025LD-Scene: LLM-Guided Diffusion for Controllable Generation of Adversarial Safety-Critical Driving Scenarioscited by 10
  4. 2025WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Drivingcited by 9
  5. 2025Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Drivingcited by 7
  6. 2025Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happencited by 5
  7. 2025Safety-Critical Traffic Simulation with Guided Latent Diffusion Modelcited by 4
  8. 2025nuPlan-R: A Closed-Loop Planning Benchmark for Autonomous Driving via Reactive Multi-Agent Simulationcited by 4
  9. 2025Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Modelscited by 3
  10. 2025RADE: Learning Risk-Adjustable Driving Environment via Multi-Agent Conditional Diffusioncited by 2
  11. 2025Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generationcited by 2
  12. 2025Optimization-Guided Diffusion for Interactive Scene Generationcited by 2
8 more
  1. 2025Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Trainingcited by 0
  2. 2026Fusing Driver Perceived and Physical Risk for Safety Critical Scenario Screening in Autonomous Drivingcited by 0
  3. 2026Emergency Lane-Change Simulation: A Behavioral Guidance Approach for Risky Scenario Generationcited by 0
  4. 2026Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Trafficcited by 0
  5. 2026KG-ASG: Collision-Knowledge-Guided Closed-Loop Adversarial Scenario Generation With Primary-Support Attributioncited by 0
  6. 2026RiskFlow: Fast and Faithful Safety-Critical Traffic Scenario Generationcited by 0
  7. 2026From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Drivingcited by 0
  8. 2026DriveCache: Action-Aware Caching for Driving World Model Inferencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Data-driven Diffusion Models for Enhancing Safety in Autonomous Vehicle Traffic Simulations
  2. 2024Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving Priors
  3. 2023SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries
  4. 2023CAT: Closed-loop Adversarial Training for Safe End-to-End Driving
  5. 2026Safety-Critical Scenarios Emerge from Initial Scenes ↗
  6. 2026Learning Responsibility-Attributed Adversarial Scenarios for Testing Autonomous Vehicles
  7. 2025Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions
  8. 2025Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles