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

• URL: http://arxiv.org/abs/2609.04912v1
• Date: Fri, 04 Sep 2026 09:15:06 GMT
• Title: TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks
• Abstract summary: TreeFI is a value-aware fault-injection methodology for FP32 single-bit faults in DNN activations and weights.<n>We validate TreeFI on CNN and Transformer models using CIFAR-10 and ImageNet.<n>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.
• Score: 1.277452693606793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption [0.0]
  This paper presents a systematic reliability characterization of pruned CKKS-encritical neural networks.<n>Polynomial-Sensitivity-Aware Pruning (PSAP) is a structured pruning method that is inherently reliability-aware.
  arXiv  Detail & Related papers  (2026-07-20T05:47:06Z)
• Categorical Robustness Assessment for Machine Learning based Network Intrusion Detection Systems [6.42094170804706]
  adversarial attacks add carefully crafted perturbations to network traffic data that leads to misclassifications.<n>This paper asks what type of architectures actually hold up when attackers try to manipulate the systems.<n>For practitioners deploying intrusion detection in adversarial environments, we recommend CNN-based architectures.
  arXiv  Detail & Related papers  (2026-06-10T13:41:44Z)
• Mitigating the ID-OOD Tradeoff in Open-Set Test-Time Adaptation [52.620992698137236]
  Open-set test-time adaptation (OSTTA) addresses the challenge of adapting models to new environments.<n>In this paper, we first analyze the limitations of entropy in OSTTA and then introduce an angular loss to regulate feature norm magnitudes.<n>Our method achieves strong OOD detection while maintaining high ID classification performance.
  arXiv  Detail & Related papers  (2026-04-02T04:00:57Z)
• Learning a Generative Meta-Model of LLM Activations [75.30161960337892]
  We create "meta-models" that learn the distribution of a network's internal states.<n>Applying the meta-model's learned prior to steering interventions improves fluency, with larger gains as loss decreases.<n>These results suggest generative meta-models offer a scalable path toward interpretability without restrictive structural assumptions.
  arXiv  Detail & Related papers  (2026-02-06T18:59:56Z)
• Fault injection analysis of Real NVP normalising flow model for satellite anomaly detection [0.22369578015657962]
  Satellites are used for a multitude of applications, including communications, Earth observation, and space science.<n>One critical application of Artificial Intelligence (AI) is fault detection.<n>Despite the advantages of neural networks, these systems are vulnerable to radiation errors, which can significantly impact their reliability.
  arXiv  Detail & Related papers  (2025-04-02T08:32:59Z)
• Conservative Prediction via Data-Driven Confidence Minimization [70.93946578046003]
  In safety-critical applications of machine learning, it is often desirable for a model to be conservative. We propose the Data-Driven Confidence Minimization framework, which minimizes confidence on an uncertainty dataset.
  arXiv  Detail & Related papers  (2023-06-08T07:05:36Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• enpheeph: A Fault Injection Framework for Spiking and Compressed Deep Neural Networks [10.757663798809144]
  We present enpheeph, a Fault Injection Framework for Spiking and Compressed Deep Neural Networks (DNNs) By injecting a random and increasing number of faults, we show that DNNs can show a reduction in accuracy with a fault rate as low as 7 x 10 (-7) faults per parameter, with an accuracy drop higher than 40%.
  arXiv  Detail & Related papers  (2022-07-31T00:30:59Z)
• Fast and Accurate Error Simulation for CNNs against Soft Errors [64.54260986994163]
  We present a framework for the reliability analysis of Conal Neural Networks (CNNs) via an error simulation engine. These error models are defined based on the corruption patterns of the output of the CNN operators induced by faults. We show that our methodology achieves about 99% accuracy of the fault effects w.r.t. SASSIFI, and a speedup ranging from 44x up to 63x w.r.t.FI, that only implements a limited set of error models.
  arXiv  Detail & Related papers  (2022-06-04T19:45:02Z)
• Test-time Batch Statistics Calibration for Covariate Shift [66.7044675981449]
  We propose to adapt the deep models to the novel environment during inference. We present a general formulation $alpha$-BN to calibrate the batch statistics. We also present a novel loss function to form a unified test time adaptation framework Core.
  arXiv  Detail & Related papers  (2021-10-06T08:45:03Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)

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.