Demystifying Network Foundation Models

• URL: http://arxiv.org/abs/2509.23089v3
• Date: Sat, 08 Nov 2025 23:32:07 GMT
• Title: Demystifying Network Foundation Models
• Authors: Sylee Beltiukov, Satyandra Guthula, Wenbo Guo, Walter Willinger, Arpit Gupta,
• Abstract summary: This work presents a systematic investigation into the latent knowledge encoded within Network Foundation Models (NFMs)<n>We evaluate four state-of-the-art NFMs, revealing that they all exhibit significant anisotropy, inconsistent feature sensitivity patterns.<n>Our work identifies numerous limitations across all models and demonstrates that addressing them can significantly improve model performance.
• Score: 14.775836458250799
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work presents a systematic investigation into the latent knowledge encoded within Network Foundation Models (NFMs) that focuses on hidden representations analysis rather than pure downstream task performance. Different from existing efforts, we analyze the models through a three-part evaluation: Embedding Geometry Analysis to assess representation space utilization, Metric Alignment Assessment to measure correspondence with domain-expert features, and Causal Sensitivity Testing to evaluate robustness to protocol perturbations. Using five diverse network datasets spanning controlled and real-world environments, we evaluate four state-of-the-art NFMs, revealing that they all exhibit significant anisotropy, inconsistent feature sensitivity patterns, an inability to separate the high-level context, payload dependency, and other properties. Our work identifies numerous limitations across all models and demonstrates that addressing them can significantly improve model performance (by up to +0.35 $F_1$ score without architectural changes).

Related papers

• From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection [2.8647133890967]
  Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiveness remains underexplored.<n>Recent work suggests that both graph neural network (GNN)-based and transformer-based models, including large language models (LLMs) yield promising results when evaluated on curated benchmark datasets.<n>In this study, we systematically evaluate two representative DL models-ReVeal and LineVul-across four representative datasets.
  arXiv  Detail & Related papers  (2025-12-11T10:04:54Z)
• Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection [36.97738113847375]
  We investigate representative vision foundation models for OOD detection.<n>A pre-trained DINOv2 model naturally provides a highly discriminative feature space for OOD detection.<n>Fine-tuning foundation models on in-domain (ID) data can enhance OOD detection.<n>We propose the Mixture of Feature Experts (MoFE) module, which partitions features into subspaces.
  arXiv  Detail & Related papers  (2025-10-12T13:00:53Z)
• 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)
• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• Towards Evaluating the Robustness of Visual State Space Models [63.14954591606638]
  Vision State Space Models (VSSMs) have demonstrated remarkable performance in visual perception tasks. However, their robustness under natural and adversarial perturbations remains a critical concern. We present a comprehensive evaluation of VSSMs' robustness under various perturbation scenarios.
  arXiv  Detail & Related papers  (2024-06-13T17:59:44Z)
• Optimizing cnn-Bigru performance: Mish activation and comparative analysis with Relu [0.0]
  Activation functions (AF) are fundamental components within neural networks, enabling them to capture complex patterns and relationships in the data. This study illuminates the effectiveness of AF in elevating the performance of intrusion detection systems.
  arXiv  Detail & Related papers  (2024-05-30T21:48:56Z)
• Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection [55.2480439325792]
  We present an in-depth evaluation of an object detection model that integrates the LSKNet backbone with the DiffusionDet head. The proposed model achieves a mean average precision (MAP) of approximately 45.7%, which is a significant improvement. This advancement underscores the effectiveness of the proposed modifications and sets a new benchmark in aerial image analysis.
  arXiv  Detail & Related papers  (2023-11-21T19:49:13Z)
• A Comprehensive Evaluation and Analysis Study for Chinese Spelling Check [53.152011258252315]
  We show that using phonetic and graphic information reasonably is effective for Chinese Spelling Check. Models are sensitive to the error distribution of the test set, which reflects the shortcomings of models. The commonly used benchmark, SIGHAN, can not reliably evaluate models' performance.
  arXiv  Detail & Related papers  (2023-07-25T17:02:38Z)
• Robustness Analysis on Foundational Segmentation Models [28.01242494123917]
  In this work, we perform a robustness analysis of Visual Foundation Models (VFMs) for segmentation tasks. We benchmark seven state-of-the-art segmentation architectures using 2 different datasets. Our findings reveal several key insights: VFMs exhibit vulnerabilities to compression-induced corruptions, despite not outpacing all of unimodal models in robustness, multimodal models show competitive resilience in zero-shot scenarios, and VFMs demonstrate enhanced robustness for certain object categories.
  arXiv  Detail & Related papers  (2023-06-15T16:59:42Z)
• Artificial Text Detection via Examining the Topology of Attention Maps [58.46367297712477]
  We propose three novel types of interpretable topological features for this task based on Topological Data Analysis (TDA) We empirically show that the features derived from the BERT model outperform count- and neural-based baselines up to 10% on three common datasets. The probing analysis of the features reveals their sensitivity to the surface and syntactic properties.
  arXiv  Detail & Related papers  (2021-09-10T12:13:45Z)
• How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models [95.8037674226622]
  We introduce a 3-dimensional evaluation metric that characterizes the fidelity, diversity and generalization performance of any generative model in a domain-agnostic fashion. Our metric unifies statistical divergence measures with precision-recall analysis, enabling sample- and distribution-level diagnoses of model fidelity and diversity.
  arXiv  Detail & Related papers  (2021-02-17T18:25:30Z)

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.