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

Taibiao Zhao; Xiang Zhang; Mingxuan Sun; Ruyi Ding; Xugui Zhou

cs.CRApr 4, 2026

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

Authors: Taibiao Zhao, Xiang Zhang, Mingxuan Sun, Ruyi Ding, Xugui Zhou

Organizations: Louisiana State University, Baton Rouge, Louisiana, USA

Abstract

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.

Autonomous Driving Safety Evaluation

Autonomous driving safety evaluation studies how to measure, test, and improve the safety of self-driving systems in routine and hazardous conditions.

See all 157 papers

TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks
Sep 4, 2026Noam Bires, Marcello Traiola, Angeliki Kritikakou +1
Univ Rennes, Inria, IRISA, CNRS, Rennes, France
Test Case Prioritization for DNNs via Neural Collapse Instability
Jul 22, 2026Chunyu Liu, Mingyuan Li, Yang Li +4Automated Software Testing DNN Testing
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China · National Engineering Research Center of Disaster Backup and Recovery, Beijing University of Posts and Telecommunications, China · Information Security Center, Beijing University of Posts and Telecommunications, China
CAFD: Concept-Aware DNN Fault Detection using VLMs
May 19, 2026Amin Abbasishahkoo, Mahboubeh Dadkhah, Lionel BriandDNN Testing Anomaly Detection
School of EECS, University of Ottawa, Ottawa, ON K1N 6N5, Canada · Research Ireland Lero centre for software, University of Limerick, Ireland

Sep 4, 2026J/K move · Enter open · S save

TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks

Noam Bires, Marcello Traiola, Angeliki Kritikakou, Elisa Fromont

Univ Rennes, Inria, IRISA, CNRS, Rennes, France

Open paper AskPDF arXiv

Reliability evaluation of deep neural networks under hardware faults commonly relies on fault injection, but exhaustive campaigns are intractable for modern models and datasets. Statistical fault injection reduces this cost, yet existing approaches still require large injection budgets because they do not explicitly exploit a key property of floating-point faults: the effect of a bit flip depends strongly on the value being corrupted. We propose TreeFI, a value-aware statistical fault-injection methodology for FP32 single-bit faults in DNN activations and weights. TreeFI partitions each layer's value distribution into intervals with similar expected bit-flip behavior, learned using regression trees, and allocates injections across these intervals according to their relevance for failure-rate estimation. This stratified allocation preserves the target confidence and error margin while avoiding unnecessary injections in low-impact regions of the fault space. We validate TreeFI on CNN and Transformer models using CIFAR-10 and ImageNet. On ResNet8, where exhaustive activation fault injection is feasible, TreeFI provides more accurate estimates than state-of-the-art statistical FI baselines under the same campaign setting. Across the evaluated models, TreeFI reduces the required injection budget by up to 72.1x, with average reductions of 44.9x for activation faults and 11.2x for the executed weight campaigns.

Abstract

Autonomous Driving Safety Evaluation

Explore similar work

TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks

Test Case Prioritization for DNNs via Neural Collapse Instability

CAFD: Concept-Aware DNN Fault Detection using VLMs