Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation

yu tsz yuk, Wentai Wu, Yuen-Ying Yeung, Weiwei Lin

Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation: 4 upvotes on Hugging Face Daily Papers, #48 of 53 papers on 2026-05-26. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.