Enhancing healthcare security: Manifold-aware machine learning for robust adversarial attack detection in IoMT networks

The widespread adoption of Internet of Medical Things (IoMT) devices and the increasing movement towards telehealth have revolutionized healthcare delivery but also introduced significant security challenges. Tiny Machine Learning (TinyML) models deployed on resource-constrained medical devices are vulnerable to adversarial attacks that can compromise patient data and device functionality, posing risks to patient safety. To address these critical security concerns, this paper proposes MARD (Manifold-Aware Robust Defense), a defense mechanism designed to enhance the robustness of TinyML models. MARD trains a compact student model by transferring knowledge from a teacher model that incorporates Graph-based Manifold Regularization (GMR) and Manifold Mixup Interpolation (MMI). GMR promotes smooth representation learning along the data manifold, while MMI encourages linearity and improves generalization across multiple hidden layers. Evaluations against various white-box and black-box adversarial attacks, including DF, PGD, BIM, DT, and CW, demonstrate that the proposed defense maintains high classification accuracy on clean data, comparable to baseline models, with minimal reductions under attack conditions. This defense offers a promising strategy for strengthening the security and reliability of IoMT systems in telehealth applications.