Abstract
Anomalous subgraph detection within networks is an important issue in many emerging applications. Existing algorithms, such as graph structure methods and spectral feature methods, usually focus on the special stochastic model (such as the Erdős-Renyi random graph) or may not efficiently extract the anomalous behaviors of the networks, which result in detection performance degradation. To mitigate the limitations, in this paper, we first present an anomalous subgraph detection framework associated with deep neural networks (DNN) for detecting anomalous behaviors within the networks. Furthermore, based on the developed framework, we propose a residual matrix-based convolutional neural network (RM-CNN) algorithm with respect to the given expected degree models, which are more general networks than the Erdős-Renyi random graphs. In particular, the trained RM-CNN can efficiently capture the anomalous changes of the network and then achieve the detection performance improvement. Simulation experiments display that the proposed RM-CNN algorithm is superior to the compared algorithms in both detection performance and detection speed.
Highlights
Network anomaly detection has become an important issue in may applications, ranging from detecting malicious attacks of wireless networks [1], [2], vehicle anomaly detection [3], to array diagnostics [4]
Based on the developed detection framework, we propose a residual matrix-based convolutional neural network (RM-CNN) algorithm for the anomalous subgraph detection associated with the given expected degree models
Based on the proposed deep neural networks (DNN)-based subgraph detection framework, we develop a RM-CNN algorithm associated with the given expected degree models to detect the anomalous behaviors of the networks
Summary
Network anomaly detection has become an important issue in may applications, ranging from detecting malicious attacks of wireless networks [1], [2], vehicle anomaly detection [3], to array diagnostics [4]. Thanks to the powerful feature extraction capability of deep learning, we extend the new tool into the anomaly detection problem for the given expected degree networks in this paper. Based on the developed detection framework, we propose a residual matrix-based convolutional neural network (RM-CNN) algorithm for the anomalous subgraph detection associated with the given expected degree models. The anomalous behavior may not be extracted and directly results in the low detection performance of the traditional algorithms To overcome those problems, our paper develops a convolutional neural network (CNN) based on the residual matrix of anomalous networks for extracting the anomalous structure. Based on the proposed DNN-based subgraph detection framework, we develop a RM-CNN algorithm associated with the given expected degree models to detect the anomalous behaviors of the networks.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
