一句话：定义诊断忠实性度量并提出 FaithLog，以因果引导注意力与对抗一致性学习实现忠实的日志异常检测。
基于日志的软件可靠性维护系统对稳定用户体验至关重要，但现有深度学习方法对服务提供者而言是黑盒，无法理解其异常判定依据，阻碍了在生产环境中的信任与部署。本文基于某大型云厂商 SRE 的调研，提出用于建立信任的可信度量——诊断忠实性，并设计两个评估任务：基于注意力的根因定位与事件扰动。实证研究表明现有方法在诊断忠实性上表现不佳。为此作者提出 FaithLog，通过精心设计的因果引导注意力机制与对抗一致性学习实现忠实性。在两个公开数据集和一个工业数据集上的评估结果表明，该方法在诊断忠实性上达到当前最优水平。
Log-based software reliability maintenance systems are crucial for sustaining stable customer experience. However, existing deep learning-based methods represent a black box for service providers, making it impossible for providers to understand how these methods detect anomalies, thereby hindering trust and deployment in real production environments. To address this issue, this paper defines a trustworthiness metric—diagnostic faithfulness—for models to gain service providers’ trust, based on surveys of SREs at a major cloud provider. We design two evaluation tasks: attention-based root cause localization and event perturbation. Empirical studies demonstrate that existing methods perform poorly in diagnostic faithfulness. Consequently, we propose FaithLog, a faithful log-based anomaly detection system, which achieves faithfulness through a carefully designed causality-guided attention mechanism and adversarial consistency learning. Evaluation results on two public datasets and one industrial dataset demonstrate that the proposed method achieves state-of-the-art performance in diagnostic faithfulness.
DOI 原文 ·
@inproceedings{paperbot9449,
title = {Walk the Talk: Is Your Log-based Software Reliability Maintenance System Really Reliable?},
author = {Minghua He and Tong Jia and Chiming Duan and Pei Xiao and Lingzhe Zhang and Kangjin Wang and Yifan Wu and Ying Li and Gang Huang},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00316}
}