A divide-and-conquer method decomposes network intrusion detection into focused subtasks, allowing lightweight models to gain up to 43.3% higher local accuracy and 257x smaller size while improving robustness and explainability.
On the role of deep learning model complexity in adversarial robustness for medical images
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust and Explainable Divide-and-Conquer Learning for Intrusion Detection
A divide-and-conquer method decomposes network intrusion detection into focused subtasks, allowing lightweight models to gain up to 43.3% higher local accuracy and 257x smaller size while improving robustness and explainability.