LiteShield uses hybrid feature selection with common classifiers to reach 98% binary and 80-85% multiclass accuracy on UNSW-NB15 while favoring Random Forest for lower model size and inference cost in IoT environments.
Attack Classification Using Machine Learning on UNSW-NB15 Dataset Using XGBoost Feature Selection and Ablation Analysis
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
-
LiteShield: Hybrid Feature Selection-Driven Lightweight Intrusion Detection for Resource-Constrained IoT Networks
LiteShield uses hybrid feature selection with common classifiers to reach 98% binary and 80-85% multiclass accuracy on UNSW-NB15 while favoring Random Forest for lower model size and inference cost in IoT environments.