K. Vamshee Krishna, Koduri Akarsh, Bethala Harsha, Poosa Vamshi, E Sainath Reddy 02 7(1) The exponential growth of InternetofThings IoT devices has drastically expanded the threat landscape yet many existing intrusion detection systems overlook the underlying graph structures within device communication networks This study proposes a comprehensive framework that integrates traditional machine learning models with a graphbased learning strategy enhanced by randomized edge perturbation aiming to achieve both high detection performance and adversarial privacy protection The approach begins with the RTIOT2022 networkflow dataset performing exploratory data analysis to uncover feature relationships and address class imbalance Categorical variables such as attack type protocol and service are encoded and SMOTE oversampling is applied to ensure balanced class distribution Dimensionality reduction using Principal Component Analysis PCA yields a compressed yet informationrich feature space Four baseline classifiersGaussian Naive Bayes GNB Linear Discriminant Analysis LDA Ridge Classifier and Decision Tree Classifier DTCare trained and evaluated using standard performance metrics To exploit graph structural information we propose a hybrid Graph Neural Networkstyle Decision Tree Classifier GNNDTC where node features are aggregated from local neighborhoods to construct decision trees that capture relational attack behaviors Additionally randomized edge perturbation is applied to mask sensitive graph topology and enhance resilience against adversarial attacks without significantly compromising accuracy Experimental results reveal that LDA and Ridge achieve accuracies of 934 and 908 respectively while GNB trails with 490 The proposed GNNDTC model achieves 997 accuracy and F1score substantially outperforming all baselines Classwise evaluations further confirm consistent performance across varied attack types These findings highlight the effectiveness of combining graphaware learning with privacypreserving perturbation for secure and robust IoT intrusion detection Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026