Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms

• URL: http://arxiv.org/abs/2606.04767v1
• Date: Wed, 03 Jun 2026 11:50:38 GMT
• Title: Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms
• Abstract summary: robustness of deep neural networks is crucial for safety-critical deployments.<n>We propose a principled, attack-agnostic robustness metric based on the spectral norm of the Fisher Information Matrix.<n>Our framework serves as an interpretable diagnostic tool that complements attack-based evaluations.
• Score: 18.10438822471092
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The robustness of deep neural networks is crucial for safety-critical deployments, yet existing evaluation methods are often attack-dependent and lack interpretability. We propose a principled, attack-agnostic robustness metric based on the spectral norm of the Fisher Information Matrix (FIM), which quantifies the worst-case sensitivity of the model's output distribution to input perturbations. Theoretically, we establish that the FIM equals the variance of the input Jacobian and derive closed-form spectral bounds for common architectures, including VGG, ResNet, DenseNet, and Transformer, providing the first theoretical robustness ranking. To enable scalable evaluation, we develop efficient algorithms, including power iteration and Hutchinson-based estimation, that support both white-box and black-box settings. Extensive experiments across multiple datasets, including CIFAR, ImageNet, and medical images, and across multiple architectures show a strong correlation between our metric and adversarial vulnerability. Our framework serves as an interpretable diagnostic tool that complements attack-based evaluations, offering insights into architectural sensitivity and guiding the design of more robust models. Code is available at: https://github.com/franz-chang/SRP/.

Related papers

• Statistical Analysis of Executability and Program Equivalence in Decompilation for IoT Vulnerability Detection [1.9637266103693347]
  We propose a nine-dimensional quality evaluation metric consisting of three categories: structural, behavioral, and semantic similarity.<n>Vulnerabilities often arise in details that are easily lost in this process, such as error-handling flows and boundary checks.<n>This study provides a statistical evaluation foundation for quantifying implementation defects in IoT devices.
  arXiv  Detail & Related papers  (2026-08-07T08:36:35Z)
• PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis [80.64607823130437]
  We extend PAC-Bayesian framework from deep neural networks to message passing GNNs.<n>We derive a tighter robust generalization bound in the adversarial setting.
  arXiv  Detail & Related papers  (2026-06-04T15:31:21Z)
• MS-ISSM: Objective Quality Assessment of Point Clouds Using Multi-scale Implicit Structural Similarity [65.85858856481131]
  unstructured and irregular nature of point clouds poses a significant challenge for objective quality assessment (PCQA)<n>We propose the Multi-scale Implicit Structural Similarity Measurement (MS-ISSM)
  arXiv  Detail & Related papers  (2026-01-03T14:58:52Z)
• Rethinking Evaluation of Infrared Small Target Detection [105.59753496831739]
  This paper introduces a hybrid-level metric incorporating pixel- and target-level performance, proposing a systematic error analysis method, and emphasizing the importance of cross-dataset evaluation.<n>An open-source toolkit has be released to facilitate standardized benchmarking.
  arXiv  Detail & Related papers  (2025-09-21T02:45:07Z)
• Evaluating Ensemble and Deep Learning Models for Static Malware Detection with Dimensionality Reduction Using the EMBER Dataset [0.0]
  This study investigates the effectiveness of several machine learning algorithms for static malware detection using the EMBER dataset.<n>We evaluate eight classification models: LightGBM, XGBoost, CatBoost, Random Forest, Extra Trees, HistGradientBoosting, k-Nearest Neighbors (KNN), and TabNet.<n>The models are assessed on accuracy, precision, recall, F1 score, and AUC to examine both predictive performance and robustness.
  arXiv  Detail & Related papers  (2025-07-22T18:45:10Z)
• MoCA: Multi-modal Cross-masked Autoencoder for Digital Health Measurements [2.8493802389913694]
  We propose the Multi-modal Cross-masked Autoencoder (MoCA), a self-supervised learning framework that combines transformer architecture with masked autoencoder (MAE) methodology.<n>MoCA demonstrates strong performance boosts across reconstruction and downstream classification tasks on diverse benchmark datasets.<n>Our approach offers a novel solution for leveraging unlabeled multi-modal wearable data while handling missing modalities, with broad applications across digital health domains.
  arXiv  Detail & Related papers  (2025-06-02T21:07:25Z)
• Evaluating Single Event Upsets in Deep Neural Networks for Semantic Segmentation: an embedded system perspective [1.474723404975345]
  This paper delves into the robustness assessment in embedded Deep Neural Networks (DNNs)<n>By scrutinizing the layer-by-layer and bit-by-bit sensitivity of various encoder-decoder models to soft errors, this study thoroughly investigates the vulnerability of segmentation DNNs to SEUs.<n>We propose a set of practical lightweight error mitigation techniques with no memory or computational cost suitable for resource-constrained deployments.
  arXiv  Detail & Related papers  (2024-12-04T18:28:38Z)
• Doubly Robust Instance-Reweighted Adversarial Training [107.40683655362285]
  We propose a novel doubly-robust instance reweighted adversarial framework. Our importance weights are obtained by optimizing the KL-divergence regularized loss function. Our proposed approach outperforms related state-of-the-art baseline methods in terms of average robust performance.
  arXiv  Detail & Related papers  (2023-08-01T06:16:18Z)
• Provable Robust Saliency-based Explanations [15.471415695449023]
  We introduce a novel metric to assess the stability of top-$k$ salient features.<n>We introduce R2ET which trains for stable explanation by efficient and effective regularizer.<n>We analyze R2ET by multi-objective optimization to prove numerical and statistical stability of explanations.
  arXiv  Detail & Related papers  (2022-12-28T22:05:32Z)
• Improving robustness of jet tagging algorithms with adversarial training [56.79800815519762]
  We investigate the vulnerability of flavor tagging algorithms via application of adversarial attacks. We present an adversarial training strategy that mitigates the impact of such simulated attacks.
  arXiv  Detail & Related papers  (2022-03-25T19:57:19Z)
• Bayesian Optimization with Machine Learning Algorithms Towards Anomaly Detection [66.05992706105224]
  In this paper, an effective anomaly detection framework is proposed utilizing Bayesian Optimization technique. The performance of the considered algorithms is evaluated using the ISCX 2012 dataset. Experimental results show the effectiveness of the proposed framework in term of accuracy rate, precision, low-false alarm rate, and recall.
  arXiv  Detail & Related papers  (2020-08-05T19:29:35Z)
• Dataless Model Selection with the Deep Frame Potential [45.16941644841897]
  We quantify networks by their intrinsic capacity for unique and robust representations. We propose the deep frame potential: a measure of coherence that is approximately related to representation stability but has minimizers that depend only on network structure. We validate its use as a criterion for model selection and demonstrate correlation with generalization error on a variety of common residual and densely connected network architectures.
  arXiv  Detail & Related papers  (2020-03-30T23:27:25Z)

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.