NetSight continually detects distribution shifts in network intrusion data and adapts a supervised model using pseudo-labeling and knowledge distillation, achieving up to 11.72% F1 improvement over methods requiring manual labeling on three long-term datasets.
Transcending transcend: Revisiting malware classification in the presence of concept drift,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Shift Detection and Adaptation for Network Intrusion Detection
NetSight continually detects distribution shifts in network intrusion data and adapts a supervised model using pseudo-labeling and knowledge distillation, achieving up to 11.72% F1 improvement over methods requiring manual labeling on three long-term datasets.