A simple graph embedding for anomaly detection in a stream of heterogeneous labeled graphs

PATTERN RECOGNITION

卷:112

Article

Kiouche, Abd Errahmane^1,2  Lagraa, Sofiane³  Amrouche, Karima²  Seba, Hamida¹ 

[1] Univ Lyon 1, Univ Lyon, CNRS, LIRIS,UMR5205, F-69622 Lyon, France

[2] Ecole Natl Super Informat Http Www Esi Dz, Lab Commun Syst Informat LCSI, BP 68M, Oued Smar 16309, Alger, Algeria

[3] Univ Luxembourg, SnT Interdisciplinary Ctr Secur Reliabil & Trust, Luxembourg, Luxembourg

关键词: Graph anomaly detection;    Graph stream;    Graph embedding;    Graph edit distance;   

DOI  :  10.1016/j.patcog.2020.107746

来源: Elsevier

【 摘 要 】

In this work, we propose a new approach to detect anomalous graphs in a stream of directed and labeled heterogeneous edges. The stream consists of a sequence of edges derived from different graphs. Each of these dynamic graphs represents the evolution of a specific activity in a monitored system whose events are acquired in real-time. Our approach is based on graph clustering and uses a simple graph embedding based on substructures and graph edit distance. Our graph representation is flexible and updates incrementally the graph vectors as soon as a new edge arrives. This allows the detection of anomalies in real-time which is an important requirement for sensitive applications such as cyber-security. Our implementation results prove the effectiveness of our approach in terms of accuracy of detection and time processing. (c) 2020 Elsevier Ltd. All rights reserved.

【 授权许可】

Free