MambaITD applies a Mamba encoder and adaptive per-user Otsu thresholding to insider threat detection, claiming higher F1 than prior methods on CERT r4.2 and r5.2, but the test-set thresholding raises concerns about the validity of the comparison.
DeepLog: Anomaly detection and diagnosis from system logs through deep learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MambaITD: An Efficient Cross-Modal Mamba Network for Insider Threat Detection
MambaITD applies a Mamba encoder and adaptive per-user Otsu thresholding to insider threat detection, claiming higher F1 than prior methods on CERT r4.2 and r5.2, but the test-set thresholding raises concerns about the validity of the comparison.