5G slice escape attack detection method based on full-flow adaptive detection

The invention discloses a 5G slice escape attack detection method based on full-flow adaptive detection. The adaptive detection of a slice escape attack is realized. Aiming at different points of slice escape attacks in the slices and among the slices, eleven-tuple features are provided, and slice e...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CHEN JINGBING, LI XIAOYONG, YUAN KAIGUO, LIU ZHENZHEN, ZHOU RUI, HUANG JINGYIN, XIANG DEJUN, HUANG ZHISHENG, HUANG KANGQIAN, HU XIN, GAO YALI, CAI BINSI
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a 5G slice escape attack detection method based on full-flow adaptive detection. The adaptive detection of a slice escape attack is realized. Aiming at different points of slice escape attacks in the slices and among the slices, eleven-tuple features are provided, and slice escape attack detection in the slices and among the slices is realized; a two-stage detection module is introduced, rapid preliminary pre-detection is carried out by using an information entropy technology, and second-stage detection recheck is carried out on traffic with abnormal pre-detection, so that the detection time is greatly shortened; a self-attention mechanism, a long-short-term memory network and a cooperative detection model are introduced, the self-attention mechanism can help to determine a feature weight, the cooperative detection model starts from a propagation link of attack traffic, and a final detection result is obtained through cooperative analysis of feature correction of an associated switch,