Network Anomalies Detection by Unsupervised Activity Deviations Extraction - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Network Anomalies Detection by Unsupervised Activity Deviations Extraction

Abstract

More and more organizations are under cyberattacks. To prevent this kind of threats, it is essential to detect them upstream by highlighting abnormal activities within networks. This paper presents our anomalies detection approach that consists of aggregating pre-processed network flows into sectors. Then for each sector, data are split into equal time periods. Finally an unsupervised clustering algorithm is employed to extract that we called activity deviations. If a specific sector network activity for one specific period differs from others, it means that a network anomaly has been detected. Our experiments are based on a real dataset provided by a French mobile operator. With our proposed method, we have been able to detect anomalies corresponding to real crowded events like fire, soccer match or concert.
Fichier principal
Vignette du fichier
network_anomalies_detection_by_unsupervised_activity_deviations_extraction.pdf (2.04 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Licence : CC BY - Attribution

Dates and versions

hal-03949960 , version 1 (24-01-2023)

Licence

Attribution

Identifiers

Cite

Christophe Maudoux, Selma Boumerdassi. Network Anomalies Detection by Unsupervised Activity Deviations Extraction. 2022 Global Information Infrastructure and Networking Symposium (GIIS), Hellenic Republic - Department of Digital Media & Communication Department of Informatics, Sep 2022, Argostoli, Greece. pp.1-5, ⟨10.1109/GIIS56506.2022.9937022⟩. ⟨hal-03949960⟩
54 View
94 Download

Altmetric

Share

Gmail Facebook X LinkedIn More