UNAD+ extends the prior UNAD system with WMV, pseudo-label supervised refinement, and explainability to reach F1 scores above 98% on CICIDS2017 and NSL-KDD while lowering false positives for unknown network attacks.
Prepare for trou- ble and make it double! supervised–unsupervised stacking for anomaly-based intrusion detection.Journal of Net- work and Computer Applications, 189:103106
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
UNAD+: An Explainable Hybrid Framework for Unknown Network Attack Detection
UNAD+ extends the prior UNAD system with WMV, pseudo-label supervised refinement, and explainability to reach F1 scores above 98% on CICIDS2017 and NSL-KDD while lowering false positives for unknown network attacks.