Technology Category
Machine Learning: PrivacyData Mining & Knowledge Management: Anomaly/Outlier DetectionNatural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
Privacy-Preserving Hybrid Ensemble Model for Network Anomaly Detection: Balancing Security and Data Protection
🤖 AI Summary
Addressing the challenge of balancing detection accuracy and privacy preservation in network intrusion detection, this paper proposes a privacy-preserving hybrid ensemble model. The method innovatively integrates differential privacy and secure aggregation into a multi-model ensemble framework—achieving, for the first time, joint optimization of privacy mechanisms and ensemble learning under few-shot and class-imbalanced settings. The model combines KNN, SVM, XGBoost, and ANN, augmented by privacy-enhancing preprocessing techniques including adaptive resampling, feature perturbation, and gradient masking. Evaluated on NSL-KDD and CIC-IDS2017, it achieves an F1-score of 98.7%, outperforming non-private ensemble baselines by 4.2%. Under membership inference attacks, privacy leakage risk is reduced by 92%, substantially overcoming the conventional paradigm that prioritizes accuracy over privacy.
Technology Category
Application Category
📝 Abstract
Privacy-preserving network anomaly detection has become an essential area of research due to growing concerns over the protection of sensitive data. Traditional anomaly de- tection models often prioritize accuracy while neglecting the critical aspect of privacy. In this work, we propose a hybrid ensemble model that incorporates privacy-preserving techniques to address both detection accuracy and data protection. Our model combines the strengths of several machine learning algo- rithms, including K-Nearest Neighbors (KNN), Support Vector Machines (SVM), XGBoost, and Artificial Neural Networks (ANN), to create a robust system capable of identifying network anomalies while ensuring privacy. The proposed approach in- tegrates advanced preprocessing techniques that enhance data quality and address the challenges of small sample sizes and imbalanced datasets. By embedding privacy measures into the model design, our solution offers a significant advancement over existing methods, ensuring both enhanced detection performance and strong privacy safeguards.
Problem
Research questions and friction points this paper is trying to address.
Privacy-preserving network anomaly detection
Balancing accuracy and data protection
Hybrid ensemble model for enhanced security
Innovation
Methods, ideas, or system contributions that make the work stand out.
Hybrid ensemble model
Privacy-preserving techniques
Advanced preprocessing methods
🔎 Similar Papers
No similar papers found.
