Iterative Selection of Categorical Variables for Log Data Anomaly Detection
Iterative Selection of Categorical Variables for Log Data Anomaly Detection
Max Landauer,Georg Höld,2 Authors,A. Rauber
2021 · DOI: 10.1007/978-3-030-88418-5_36
European Symposium on Research in Computer Security · 3 Citations
TLDR
The Variable Correlation Detector (VCD) is proposed that employs a sequence of selection constraints to disclose pairs of variables with correlating values and is capable of detecting attacks such as scans and brute-force intrusions with higher accuracy than existing detectors.