Robustness in TinyML: A Systematic Literature Review
Open Access
- 11 June 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 25 (5) , 1-37
Abstract
TinyML enables the deployment of machine learning models on low-power embedded devices, offering energy-efficient solutions for real-world applications. However, TinyML faces significant challenges due to strict memory, processing, and energy constraints, making the implementation of robust and scalable models particularly difficult. Robustness in this context refers to the ability of models to maintain stable performance under adversarial conditions, sensor noise, and environmental variability, which makes it an essential requirement for reliable deployment in practical scenarios. This study conducts a systematic literature review to examine how robustness is assessed in TinyML, analyzing key factors such as input data types, accessibility of the dataset, real vs. simulated data usage, application domains, evaluated robustness types, hardware constraints, and commonly used performance metrics. The findings show a strong preference for sensor-based inputs, public and real-world datasets, and a focus on noise-related robustness challenges. Memory efficiency stands out as the main hardware constraint, while accuracy is the most used evaluation metric, reflecting the dominance of classification tasks in TinyML research. These insights provide a structured overview of current trends and reveal key gaps in TinyML robustness research, such as the lack of standardized benchmarking frameworks and the need for more advanced adversarial defense mechanisms tailored to low-power environments. They also highlight opportunities for integrating federated and physics-informed learning approaches, promoting the development of more secure, efficient, and resilient embedded machine learning systems.Keywords
This publication has 44 references indexed in Scilit:
- Robustness in deep learning models for medical diagnostics: security and adversarial challenges towards robust AI applicationsArtificial Intelligence Review, 2024
- Optimized Tiny Machine Learning and Explainable AI for Trustable and Energy-Efficient Fog-Enabled Healthcare Decision Support SystemInternational Journal of Computational Intelligence Systems, 2024
- A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and RethinkingInternational Journal of Computer Vision, 2024
- TinyML-Raman: A novel IoT based field-deployable spectra analysis for accurate identification of pharmaceuticals and trace dye-pesticide mixtures from facile SERS methodAnalytica Chimica Acta, 2024
- Real-Time Stress Detection from Raw Noisy PPG Signals Using LSTM Model Leveraging TinyMLArabian Journal for Science and Engineering, 2024
- RobustMQ: benchmarking robustness of quantized modelsVisual Intelligence, 2023
- Fully Onboard Single Pedestrian Tracking on Nano-UAV PlatformJournal of Intelligent & Robotic Systems, 2023
- Analysing Robustness of Tiny Deep Neural Networks2023
- LimitAccess: on-device TinyML based robust speech recognition and age classificationDiscover Artificial Intelligence, 2023
- Robustness of deep learning models on graphs: A surveyAI Open, 2021