mlsanityData to 14 Oct 2026

Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)

arXiv 2604.03753 ↗First posted 4 Apr 2026cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Modern advanced driver assistance systems (ADAS) rely on deep neural networks (DNNs) for perception and planning. Since DNNs' parameters reside in DRAM during inference, bit flips caused by cosmic radiation or low-voltage operation may corrupt DNN computations, distort driving decisions, and lead to real-world incidents. This paper presents a SpatioTemporal-Aware Fault Injection (STAFI) framework to locate critical fault sites in DNNs for ADAS efficiently. Spatially, we propose a Progressive Metric-guided Bit Search (PMBS) that efficiently identifies critical network weight bits whose corruption causes the largest deviations in driving behavior (e.g., unintended acceleration or steering). Furthermore, we develop a Critical Fault Time Identification (CFTI) mechanism that determines when to trigger these faults, taking into account the context of real-time systems and environmental states, to maximize the safety impact. Experiments on DNNs for a production ADAS demonstrate that STAFI uncovers 29.56x more hazard-inducing critical faults than the strongest baseline.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 35 references that are in the map. First posted on arXiv 4 Apr 2026.

Builds on

19 of 35 references.

References · 19

  1. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  2. 2019Importance Estimation for Neural Network Pruningcited by 541
  3. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 251
  4. 2019Bit-Flip Attack: Crushing Neural Network with Progressive Bit Searchcited by 108
  5. 2018Baidu Apollo EM Motion Plannercited by 100
  6. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 72
  7. 2019Adversarial camera stickers: A physical camera-based attack on deep learning systemscited by 70
  8. 2018A Commute in Data: The comma2k19 Datasetcited by 33
  9. 2019ML-based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injectioncited by 16
  10. 2023SlowTrack: Increasing the Latency of Camera-based Perception in Autonomous Driving Using Adversarial Examplescited by 15
  11. 2023One-bit Flip is All You Need: When Bit-flip Attack Meets Model Trainingcited by 14
  12. 2025GPUHammer: Rowhammer Attacks on GPU Memories are Practicalcited by 11
7 more
  1. 2020ML-driven Malware that Targets AV Safetycited by 9
  2. 2018Experimental Resilience Assessment of An Open-Source Driving Agentcited by 6
  3. 2021Data-driven Design of Context-aware Monitors for Hazard Prediction in Artificial Pancreas Systemscited by 5
  4. 2022Strategic Safety-Critical Attacks Against an Advanced Driver Assistance Systemcited by 4
  5. 2019Kayotee: A Fault Injection-based System to Assess the Safety and Reliability of Autonomous Vehicles to Faults and Errorscited by 3
  6. 2018Seeing isn't Believing: Practical Adversarial Attack Against Object Detectorscited by 1
  7. 2023Runtime Stealthy Perception Attacks against DNN-based Adaptive Cruise Control Systemscited by 1

Built on by

Not cited yet.