Security Threats and AI-Based Detection Techniques in IoT Chips
Open Access
Abstract
The rapid expansion of the Internet of Things (IoT) has opened resource-limited devices to novel physical threats, such as Side-Channel Attacks (SCAs) and Hardware Trojans (HTs). Traditional security mechanisms are often not capable of standing against such hardware-based attacks, specifically on low-power System-on-Chip (SoC) where static defenses can incur 2× to 3× overhead in silicon area and power. Herein, the gap between hardware security and embedded AI is compositionally formulated for discussion. We present a comprehensive survey of the current hardware threat landscape and analyze the emergence of “Secure-by-Design” paradigms, specifically focusing on the integration of Edge AI and TinyML as active, on-chip intrusion detection mechanisms. This review presents a critical analysis of trade-offs for running lightweight ML models on hardware by comparing state-of-the-art approaches. Our analysis highlights that optimized architectures, such as Mamba-Enhanced Convolutional Neural Networks (CNNs) and Gated Recurrent Unit (GRU), can achieve detection accuracies exceeding 99% against SCA and >92% against stealthy Hardware Trojans, while offering up to 75% lower power consumption compared to standard deep learning baselines. Finally, open challenges such as adversarial attacks on defense models are briefly discussed, and the focus is put on future directions toward constructing secure chips based on robust, AI-driven technology.Keywords
This publication has 37 references indexed in Scilit:
- NtNDet: Hardware Trojan detection based on pre-trained language modelsExpert Systems with Applications, 2025
- Enhancing deep learning-based side-channel analysis using feature engineering in a fully simulated IoT systemExpert Systems with Applications, 2024
- One for All, All for Ascon: Ensemble-Based Deep Learning Side-Channel Analysis2024
- AI-Driven Big Data Quality Improvement for Efficient Threat Detection in Agricultural IoT Systems2024
- Autoencoders and their applications in machine learning: a surveyArtificial Intelligence Review, 2024
- Differential fault analysis attack-tolerant hardware implementation of AESThe Journal of Supercomputing, 2023
- Vehicle Computing: Vision and challengesJournal of Information and Intelligence, 2022
- A review on TinyML: State-of-the-art and prospectsJournal of King Saud University Computer and Information Sciences, 2022
- Differential Power Analysis2008
- Choosing a means of implementation1998