SHIELD-IDS: Structurally Heterogeneous Ensemble with Integrated Layered Defense for Intrusion Detection Systems
Researchers have developed SHIELD-IDS, an enhanced intrusion detection system designed to combat adversarial attacks on machine learning models. The system integrates gradient boosting models like XGBoost and LightGBM into a diverse ensemble, protected by a three-layer defense mechanism. Experiments show SHIELD-IDS maintains over 99% detection accuracy on clean data and demonstrates improved robustness against common adversarial attack methods. AI
IMPACT Enhances the security of ML-based intrusion detection systems against adversarial manipulation.