Graph Regularized Deep Sparse Representation for Unsupervised Anomaly Detection

Abstract

Anomaly detection (AD) aims to distinguish the data points that are inconsistent with the overall pattern of the data. Recently, unsupervised anomaly detection methods have aroused huge attention. Among these methods, feature representation (FR) plays an important role, which can directly affect the performance of anomaly detection. Sparse representation (SR) can be regarded as one of matrix factorization (MF) methods, which is a powerful tool for FR. However, there are some limitations in the original SR. On the one hand, it just learns the shallow feature representations, which leads to the poor performance for anomaly detection. On the other hand, the local geometry structure information of data is ignored. To address these shortcomings, a graph regularized deep sparse representation (GRDSR) approach is proposed for unsupervised anomaly detection in this work. In GRDSR, a deep representation framework is first designed by extending the single layer MF to a multilayer MF for extracting hierarchical structure from the original data. Next, a graph regularization term is introduced to capture the intrinsic local geometric structure information of the original data during the process of FR, making the deep features preserve the neighborhood relationship well. Then, a L1-norm-based sparsity constraint is added to enhance the discriminant ability of the deep features. Finally, a reconstruction error is applied to distinguish anomalies. In order to demonstrate the effectiveness of the proposed approach, we conduct extensive experiments on ten datasets. Compared with the state-of-the-art methods, the proposed approach can achieve the best performance.

Design of Graph-Based Layered Learning-Driven Model for Anomaly Detection in Distributed Cloud IoT Network

“…Injecting graphs to show network links and also to show that agents are very effective in terms of speedy recovery from an attack, even if a significant number of nodes are compromised. To our knowledge, graph-based learning models have never been widely used in IoT communication environments, and have never been used to identify dangerous sources or predict future attacks [18,19].…”

Design and Analysis of Multilayered Neural Network-Based Intrusion Detection System in the Internet of Things Network

“…There are a lot of factors to consider when designing solutions for the Internet of Things, including the sheer number of interconnected gadgets, the level of complexity involved, the prevalence of competing trends, and the wide range of variables that must be managed. The present security methods are only suitable for brief sessions on powerful computers [ 3 ].…”