Robustness Analysis of Machine Learning Models for IoT Intrusion Detection Under Data Poisoning Attacks
For IoT security practitioners, it empirically demonstrates the vulnerability of common ML-based intrusion detection systems to data poisoning, highlighting the need for robust training and monitoring.
This study evaluates four classifiers (Random Forest, GBM, Logistic Regression, DNN) against data poisoning attacks on three IoT datasets, finding that Logistic Regression and DNN suffer up to 40% degradation under label manipulation and outlier attacks, while ensemble models are more stable.
Ensuring the reliability of machine learning-based intrusion detection systems remains a critical challenge in Internet of Things (IoT) environments, particularly as data poisoning attacks increasingly threaten the integrity of model training pipelines. This study evaluates the susceptibility of four widely used classifiers, Random Forest, Gradient Boosting Machine, Logistic Regression, and Deep Neural Network models, against multiple poisoning strategies using three real-world IoT datasets. Results show that while ensemble-based models exhibit comparatively stable performance, Logistic Regression and Deep Neural Networks suffer degradation of up to 40% under label manipulation and outlier-based attacks. Such disruptions significantly distort decision boundaries, reduce detection fidelity, and undermine deployment readiness. The findings highlight the need for adversarially robust training, continuous anomaly monitoring, and feature-level validation within operational Network Intrusion Detection Systems. The study also emphasizes the importance of integrating resilience testing into regulatory and compliance frameworks for AI-driven IoT security. Overall, this work provides an empirical foundation for developing more resilient intrusion detection pipelines and informs future research on adaptive, attack-aware models capable of maintaining reliability under adversarial IoT conditions.