Few-Shot Log Anomaly Detection Based on Matching Networks

In order to address the problem of log anomaly detection in scenarios with limited labeled log datasets, this paper proposes Log-MatchNet, a novel few-shot log anomaly detection method. To tackle issues such as unstructured log data, diversity, and evolution over time, we employ structured processing and log parsing to convert log content information and template ID into vectors. Feature extraction is performed using the BERT model. Additionally, by integrating multiple datasets and conducting post-training on the BERT model for domain adaptation, we obtain
$BERT\_{}Post$
, a module with universal feature extraction capabilities in the log domain. Compared to
$BERT_{base}$
and CyBERT, our method demonstrates superior performance in log anomaly detection, especially in situations with limited labeled datasets. With only 2 annotated normal logs and 2 annotated abnormal logs,
$BERT\_{}Post$
achieves a remarkable 16.14% increase in F1-score. Addressing the challenge of imbalanced data, we introduce a matching network that learns the similarity scores between input and prototype vectors, showcasing strong generalization capabilities with an average accuracy of 99.6%. In few-shot scenarios, our method, Log-MatchNet outperforms traditional methods and Proto-Siamese network in terms of F1-score. In an unstable log evolution environment, our method exhibits robustness against noisy data, achieving an F1-score of 81.2% even with 20% injected noise. Compared to LogAnMeta, our approach yields a 31.71% increase in F1-score. Experimental results demonstrate the effectiveness of Log-MatchNet in detecting anomalies in the presence of limited labeled log data and its robust performance in log evolution scenarios.