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

• URL: http://arxiv.org/abs/2604.03753v2
• Date: Fri, 10 Apr 2026 20:25:41 GMT
• Title: Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)
• Abstract summary: Modern driver assistance systems rely on deep neural networks (DNNs) for perception and planning.<n> STAFI is a framework to locate critical fault sites in DNNs for ADAS efficiently.<n>PMBS identifies critical network weight bits whose corruption causes the largest deviations in driving behavior.<n>CFTI determines when to trigger faults, taking into account the context of real-time systems and environmental states.
• Score: 13.57717591777529
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• MDHP-Net: Detecting an Emerging Time-exciting Threat in IVN [42.74889568823579]
  We identify a new time-exciting threat model against in-vehicle network (IVN)<n>These attacks inject malicious messages that exhibit a time-exciting effect, gradually manipulating network traffic to disrupt vehicle operations and compromise safety-critical functions.<n>To detect time-exciting threat, we introduce MDHP-Net, leveraging Multi-Dimentional Hawkes Process (MDHP) and temporal and message-wise feature extracting structures.
  arXiv  Detail & Related papers  (2025-04-16T08:41:24Z)
• Mitigating multiple single-event upsets during deep neural network inference using fault-aware training [0.0]
  Deep neural networks (DNNs) are increasingly used in safety-critical applications.<n>This study analyses the impact of multiple single-bit single-event upsets in DNNs by performing fault injection at the level of a model.<n>A fault aware training (FAT) methodology is proposed that improves the DNNs' robustness to faults without any modification to the hardware.
  arXiv  Detail & Related papers  (2025-02-13T14:43:22Z)
• Advanced technology in railway track monitoring using the GPR Technique: A Review [41.94295877935867]
  Ground Penetrating Radar (GPR) is an electromagnetic survey technique that can be used to monitor railway tracks.<n>It can detect defects such as ballast pockets, fouled ballast, poor drainage, and subgrade settlement.<n>This paper demonstrates the current techniques for using synthetic modeling to calibrate real-world GPR data.<n>Deep learning techniques, particularly Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are also highlighted for their effectiveness in recognizing patterns associated with defects in GPR images.
  arXiv  Detail & Related papers  (2025-01-19T18:01:39Z)
• MDHP-Net: Detecting an Emerging Time-exciting Threat in IVN [42.74889568823579]
  We identify a new time-exciting threat model against in-vehicle network (IVN)<n>These attacks inject malicious messages that exhibit a time-exciting effect, gradually manipulating network traffic to disrupt vehicle operations and compromise safety-critical functions.<n>To detect time-exciting threat, we introduce MDHP-Net, leveraging Multi-Dimentional Hawkes Process (MDHP) and temporal and message-wise feature extracting structures.
  arXiv  Detail & Related papers  (2024-11-15T15:05:01Z)
• SpikingJET: Enhancing Fault Injection for Fully and Convolutional Spiking Neural Networks [37.89720165358964]
  SpikingJET is a novel fault injector designed specifically for fully connected and convolutional Spiking Neural Networks (SNNs) Our work underscores the critical need to evaluate the resilience of SNNs to hardware faults, considering their growing prominence in real-world applications.
  arXiv  Detail & Related papers  (2024-03-30T14:51:01Z)
• Harnessing Neuron Stability to Improve DNN Verification [42.65507402735545]
  We present VeriStable, a novel extension of recently proposed DPLL-based constraint DNN verification approach. We evaluate the effectiveness of VeriStable across a range of challenging benchmarks including fully-connected feed networks (FNNs), convolutional neural networks (CNNs) and residual networks (ResNets) Preliminary results show that VeriStable is competitive and outperforms state-of-the-art verification tools, including $alpha$-$beta$-CROWN and MN-BaB, the first and second performers of the VNN-COMP, respectively.
  arXiv  Detail & Related papers  (2024-01-19T23:48:04Z)
• Special Session: Approximation and Fault Resiliency of DNN Accelerators [0.9126382223122612]
  This paper explores the approximation and fault resiliency of Deep Neural Network accelerators. We propose to use approximate (AxC) arithmetic circuits to emulate errors in hardware without performing fault injection on the DNN. We also propose a fine-grain analysis of fault resiliency by examining fault propagation and masking in networks.
  arXiv  Detail & Related papers  (2023-05-31T19:27:45Z)
• Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators [6.8082132475259405]
  This paper focuses on quantifying the accuracy given that a transient error has occurred, which tells us how well a network behaves when a transient error occurs. We show that existing Resiliency Accuracy (RA) formulation is fundamentally inaccurate, because it incorrectly assumes that software variables have equal faulty probability under hardware transient faults. We present an algorithm that captures the faulty probabilities of DNN variables under transient faults and, thus, provides correct RA estimations validated by hardware.
  arXiv  Detail & Related papers  (2022-12-05T23:16:20Z)
• Ranking-Based Physics-Informed Line Failure Detection in Power Grids [66.0797334582536]
  Real-time and accurate detecting of potential line failures is the first step to mitigating the extreme weather impact and activating emergency controls. Power balance equations nonlinearity, increased uncertainty in generation during extreme events, and lack of grid observability compromise the efficiency of traditional data-driven failure detection methods. This paper proposes a Physics-InformEd Line failure Detector (FIELD) that leverages grid topology information to reduce sample and time complexities and improve localization accuracy.
  arXiv  Detail & Related papers  (2022-08-31T18:19:25Z)
• RL-DistPrivacy: Privacy-Aware Distributed Deep Inference for low latency IoT systems [41.1371349978643]
  We present an approach that targets the security of collaborative deep inference via re-thinking the distribution strategy. We formulate this methodology, as an optimization, where we establish a trade-off between the latency of co-inference and the privacy-level of data.
  arXiv  Detail & Related papers  (2022-08-27T14:50:00Z)
• Fault-Aware Design and Training to Enhance DNNs Reliability with Zero-Overhead [67.87678914831477]
  Deep Neural Networks (DNNs) enable a wide series of technological advancements. Recent findings indicate that transient hardware faults may corrupt the models prediction dramatically. In this work, we propose to tackle the reliability issue both at training and model design time.
  arXiv  Detail & Related papers  (2022-05-28T13:09:30Z)
• FitAct: Error Resilient Deep Neural Networks via Fine-Grained Post-Trainable Activation Functions [0.05249805590164901]
  Deep neural networks (DNNs) are increasingly being deployed in safety-critical systems such as personal healthcare devices and self-driving cars. In this paper, we propose FitAct, a low-cost approach to enhance the error resilience of DNNs by deploying fine-grained post-trainable activation functions.
  arXiv  Detail & Related papers  (2021-12-27T07:07:50Z)
• Towards Adversarial-Resilient Deep Neural Networks for False Data Injection Attack Detection in Power Grids [7.351477761427584]
  False data injection attacks (FDIAs) pose a significant security threat to power system state estimation. Recent studies have proposed machine learning (ML) techniques, particularly deep neural networks (DNNs)
  arXiv  Detail & Related papers  (2021-02-17T22:26:34Z)
• Exploring Fault-Energy Trade-offs in Approximate DNN Hardware Accelerators [2.9649783577150837]
  We present an extensive layer-wise and bit-wise fault resilience and energy analysis of different AxDNNs. Our results demonstrate that the fault resilience in AxDNNs is to the energy efficiency.
  arXiv  Detail & Related papers  (2021-01-08T05:52:12Z)
• Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks [46.731211379810105]
  We propose a fault sneaking attack on deep neural networks (DNNs)<n>The adversary aims to misclassify certain input images into any target labels by modifying the DNN parameters.<n>We show that the proposed framework can inject multiple sneaking faults without losing the overall test accuracy performance.
  arXiv  Detail & Related papers  (2019-05-28T18:56:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.