mlsanityData to 14 Oct 2026

SlowTrack: Increasing the Latency of Camera-based Perception in Autonomous Driving Using Adversarial Examples

arXiv 2312.09520 ↗First posted 15 Dec 2023cs.CV cs.CRcited by 15

Not on the map. Why?

Abstract (arXiv)

In Autonomous Driving (AD), real-time perception is a critical component responsible for detecting surrounding objects to ensure safe driving. While researchers have extensively explored the integrity of AD perception due to its safety and security implications, the aspect of availability (real-time performance) or latency has received limited attention. Existing works on latency-based attack have focused mainly on object detection, i.e., a component in camera-based AD perception, overlooking the entire camera-based AD perception, which hinders them to achieve effective system-level effects, such as vehicle crashes. In this paper, we propose SlowTrack, a novel framework for generating adversarial attacks to increase the execution time of camera-based AD perception. We propose a novel two-stage attack strategy along with the three new loss function designs. Our evaluation is conducted on four popular camera-based AD perception pipelines, and the results demonstrate that SlowTrack significantly outperforms existing latency-based attacks while maintaining comparable imperceptibility levels. Furthermore, we perform the evaluation on Baidu Apollo, an industry-grade full-stack AD system, and LGSVL, a production-grade AD simulator, with two scenarios to compare the system-level effects of SlowTrack and existing attacks. Our evaluation results show that the system-level effects can be significantly improved, i.e., the vehicle crash rate of SlowTrack is around 95% on average while existing works only have around 30%.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 17 of its 39 references that are in the map. First posted on arXiv 15 Dec 2023.

Builds on

17 of 39 references.

References · 17

  1. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  2. 2016Simple Online and Realtime Trackingcited by 868
  3. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 823
  4. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 532
  5. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 490
  6. 2020LGSVL Simulator: A High Fidelity Simulator for Autonomous Drivingcited by 121
  7. 2020Sponge Examples: Energy-Latency Attacks on Neural Networkscited by 111
  8. 2021Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attackscited by 101
  9. 2018Interpretable Deep Learning under Firecited by 74
  10. 2020Dirty Road Can Attack: Security of Deep Learning based Automated Lane Centering under Physical-World Attackcited by 64
  11. 2020A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inferencecited by 61
  12. 2023Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attackcited by 37
5 more
  1. 2022Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectorscited by 28
  2. 2022SoK: On the Semantic AI Security in Autonomous Drivingcited by 22
  3. 2023Overload: Latency Attacks on Object Detection for Edge Devicescited by 13
  4. 2022Too Afraid to Drive: Systematic Discovery of Semantic DoS Vulnerability in Autonomous Driving Planning under Physical-World Attackscited by 11
  5. 2020Security of Deep Learning based Lane Keeping System under Physical-World Adversarial Attackcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 6; 2026: 2.

15 papers.

Sort:

By area:

  1. 2024Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Drivingcited by 32
  2. 2025ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinkingcited by 23
  3. 2024ControlLoc: Physical-World Hijacking Attack on Visual Perception in Autonomous Drivingcited by 6
  4. 2024Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspectivecited by 6
  5. 2024SlowPerception: Physical-World Latency Attack against Visual Perception in Autonomous Drivingcited by 3
  6. 2024A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous Drivingcited by 3
  7. 2024Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devicescited by 3
  8. 2024Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attackscited by 2
  9. 2025BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Modelscited by 2
  10. 2025Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insightscited by 2
  11. 2025EO-VLM: VLM-Guided Energy Overload Attacks on Vision Modelscited by 1
  12. 2025Efficiency Robustness of Dynamic Deep Learning Systemscited by 1
3 more
  1. 2025T2I-Based Physical-World Appearance Attack against Traffic Sign Recognition Systems in Autonomous Drivingcited by 0
  2. 2026Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)cited by 0
  3. 2026AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelinescited by 0