مورد إلكتروني
Supervised contrastive learning over prototype-label embeddings for network intrusion detection
| العنوان: | Supervised contrastive learning over prototype-label embeddings for network intrusion detection |
|---|---|
| بيانات النشر: | Elsevier 2022 |
| تفاصيل مُضافة: | López Martín, Manuel |
| نوع الوثيقة: | Electronic Resource |
| مستخلص: | Producción Científica Contrastive learning makes it possible to establish similarities between samples by comparing their distances in an intermediate representation space (embedding space) and using loss functions designed to attract/repel similar/dissimilar samples. The distance comparison is based exclusively on the sample features. We propose a novel contrastive learning scheme by including the labels in the same embedding space as the features and performing the distance comparison between features and labels in this shared embedding space. Following this idea, the sample features should be close to its ground-truth (positive) label and away from the other labels (negative labels). This scheme allows to implement a supervised classification based on contrastive learning. Each embedded label will assume the role of a class prototype in embedding space, with sample features that share the label gathering around it. The aim is to separate the label prototypes while minimizing the distance between each prototype and its same-class samples. A novel set of loss functions is proposed with this objective. Loss minimization will drive the allocation of sample features and labels in embedding space. Loss functions and their associated training and prediction architectures are analyzed in detail, along with different strategies for label separation. The proposed scheme drastically reduces the number of pair-wise comparisons, thus improving model performance. In order to further reduce the number of pair-wise comparisons, this initial scheme is extended by replacing the set of negative labels by its best single representative: either the negative label nearest to the sample features or the centroid of the cluster of negative labels. This idea creates a new subset of models which are analyzed in detail. The outputs of the proposed models are the distances (in embedding space) between each sample and the label prototypes. These distances can be used to perform classification (minimum distance lab Ministerio de Ciencia, Innovación y Universidades - Agencia Estatal de Investigación - Fondo Europeo de Desarrollo Regional (grant RTI2018-098958-B-I00) |
| مصطلحات الفهرس: | Label embedding, Incrustación de etiquetas, Contrastive learning, Aprendizaje contrastivo, Network intrusion detection, Detección de intrusos en red, info:eu-repo/semantics/article, info:eu-repo/semantics/publishedVersion |
| URL: | |
| الإتاحة: | Open access content. Open access content Attribution-NonCommercial-NoDerivatives 4.0 Internacional info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-nd/4.0 © 2021 Elsevier |
| ملاحظة: | application/pdf English |
| أرقام أخرى: | ESUDE oai:uvadoc.uva.es:10324/48972 https://doi.org/10.1016/j.inffus.2021.09.014 Information Fusion, 2022, vol. 79, p. 200-228 1566-2535 https://uvadoc.uva.es/handle/10324/48972 1365872059 |
| المصدر المساهم: | UNIVERSIDAD DE VALLADOLID From OAIster®, provided by the OCLC Cooperative. |
| رقم الأكسشن: | edsoai.on1365872059 |
| قاعدة البيانات: | OAIster |
كن أول من يترك تعليقا!