2 papers
cs.LG2024
Deep Learning for Network Anomaly Detection under Data Contamination: Evaluating Robustness and Mitigating Performance Degradation
D'Jeff K. Nkashama, Jordan Masakuna Félicien, Arian Soltani +4
Deep learning (DL) has emerged as a crucial tool in network anomaly detection (NAD) for cybersecurity. While DL models for anomaly detection excel at extracting features and learni…
cs.LG2024
Impact of Inaccurate Contamination Ratio on Robust Unsupervised Anomaly Detection
Jordan F. Masakuna, DJeff Kanda Nkashama, Arian Soltani +3
Training data sets intended for unsupervised anomaly detection, typically presumed to be anomaly-free, often contain anomalies (or contamination), a challenge that significantly un…