Boundary-Aware Contrastive Learning for Log Anomaly Detection

Log anomaly detection in modern distributed systems is challenging. Anomalous behaviors are rare. Manual labeling is expensive. Session boundaries are often set by fixed heuristics before model training. This fixed-boundary assumption is problematic because segmentation errors propagate into represe...

Descripció completa

Dades bibliogràfiques

Autors principals:	Fouad Ailabouni, Jesús-Ángel Román-Gallego, María-Luisa Pérez-Delgado, Laura Grande Pérez
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2026-03-01
Col·lecció:	Applied Sciences
Matèries:	log anomaly detection contrastive learning session segmentation self-supervised learning zero-shot detection LSTM
Accés en línia:	https://www.mdpi.com/2076-3417/16/7/3208
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!