Salvato in:
Dettagli Bibliografici
Autori principali: Wong, Yutszyuk, Wu, Wentai, Yeung, Yuen-Ying, Lin, Weiwei
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.10988
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914555184021504
author Wong, Yutszyuk
Wu, Wentai
Yeung, Yuen-Ying
Lin, Weiwei
author_facet Wong, Yutszyuk
Wu, Wentai
Yeung, Yuen-Ying
Lin, Weiwei
contents Log anomaly detection is a critical task for system operations and security assurance. However, in networked systems at scale, log data are generated at massive scale while instance-level annotations are prohibitively expensive, posing great difficulties to fine-grained anomaly localization. To address this challenge, we propose LogMILP (Log anomaly localization based on Multi-Instance Learning enhanced by prototypes and Perturbation), a weakly supervised framework that enables both bag-level anomaly detection and instance-level anomaly localization using only bag-level labels. Our method guides the model to pinpoint the critical log entries using prototype-guided structural modeling with counterfactual perturbation consistency regularization, thereby improving localization reliability and interpretability under coarse-grained supervision. Experimental results on three public datasets demonstrate that LogMILP achieves competitive detection performance while yielding significantly more reliable instance-level localization. Our code is open-sourced at https://github.com/YUK1207/LogMILP.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10988
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation
Wong, Yutszyuk
Wu, Wentai
Yeung, Yuen-Ying
Lin, Weiwei
Machine Learning
Artificial Intelligence
Log anomaly detection is a critical task for system operations and security assurance. However, in networked systems at scale, log data are generated at massive scale while instance-level annotations are prohibitively expensive, posing great difficulties to fine-grained anomaly localization. To address this challenge, we propose LogMILP (Log anomaly localization based on Multi-Instance Learning enhanced by prototypes and Perturbation), a weakly supervised framework that enables both bag-level anomaly detection and instance-level anomaly localization using only bag-level labels. Our method guides the model to pinpoint the critical log entries using prototype-guided structural modeling with counterfactual perturbation consistency regularization, thereby improving localization reliability and interpretability under coarse-grained supervision. Experimental results on three public datasets demonstrate that LogMILP achieves competitive detection performance while yielding significantly more reliable instance-level localization. Our code is open-sourced at https://github.com/YUK1207/LogMILP.
title Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.10988