Generality Is Not Enough: Zero-Label Cross-System Log-Based Anomaly Detection via Knowledge-Level Collaboration
By: Xinlong Zhao , Tong Jia , Minghua He and more
Potential Business Impact:
Finds computer problems without needing examples.
Log-based anomaly detection is crucial for ensuring software system stability. However, the scarcity of labeled logs limits rapid deployment to new systems. Cross-system transfer has become an important research direction. State-of-the-art approaches perform well with a few labeled target logs, but limitations remain: small-model methods transfer general knowledge but overlook mismatches with the target system's proprietary knowledge; LLM-based methods can capture proprietary patterns but rely on a few positive examples and incur high inference cost. Existing LLM-small model collaborations route 'simple logs' to the small model and 'complex logs' to the LLM based on output uncertainty. In zero-label cross-system settings, supervised sample complexity is unavailable, and such routing does not consider knowledge separation. To address this, we propose GeneralLog, a novel LLM-small model collaborative method for zero-label cross-system log anomaly detection. GeneralLog dynamically routes unlabeled logs, letting the LLM handle 'proprietary logs' and the small model 'general logs,' enabling cross-system generalization without labeled target logs. Experiments on three public log datasets show that GeneralLog achieves over 90% F1-score under a fully zero-label setting, significantly outperforming existing methods.
Similar Papers
ZeroLog: Zero-Label Generalizable Cross-System Log-based Anomaly Detection
Software Engineering
Finds computer problems without needing examples.
FusionLog: Cross-System Log-based Anomaly Detection via Fusion of General and Proprietary Knowledge
Machine Learning (CS)
Finds computer problems without needing examples.
Log Anomaly Detection with Large Language Models via Knowledge-Enriched Fusion
Artificial Intelligence
Finds computer problems by understanding log messages.