TinyML Security: Exploring Vulnerabilities in Resource-Constrained Machine Learning Systems
Not on the map. Why?
Abstract (arXiv)
Tiny Machine Learning (TinyML) systems, which enable machine learning inference on highly resource-constrained devices, are transforming edge computing but encounter unique security challenges. These devices, restricted by RAM and CPU capabilities two to three orders of magnitude smaller than conventional systems, make traditional software and hardware security solutions impractical. The physical accessibility of these devices exacerbates their susceptibility to side-channel attacks and information leakage. Additionally, TinyML models pose security risks, with weights potentially encoding sensitive data and query interfaces that can be exploited. This paper offers the first thorough survey of TinyML security threats. We present a device taxonomy that differentiates between IoT, EdgeML, and TinyML, highlighting vulnerabilities unique to TinyML. We list various attack vectors, assess their threat levels using the Common Vulnerability Scoring System, and evaluate both existing and possible defenses. Our analysis identifies where traditional security measures are adequate and where solutions tailored to TinyML are essential. Our results underscore the pressing need for specialized security solutions in TinyML to ensure robust and secure edge computing applications. We aim to inform the research community and inspire innovative approaches to protecting this rapidly evolving and critical field.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 23 of its 131 references that are in the map. First posted on arXiv 11 Nov 2024.
Builds on
23 of 131 references.
References · 23
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
- 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
- 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
- 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 456
- 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 324
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
- 2021Adversarial Unlearning of Backdoors via Implicit Hypergradientcited by 166
- 2018PRADA: Protecting against DNN Model Stealing Attackscited by 165
- 2020Rethinking the Trigger of Backdoor Attackcited by 77
- 2021Trigger Hunting with a Topological Prior for Trojan Detectioncited by 39
11 more
- 2023A Machine Learning-oriented Survey on Tiny Machine Learningcited by 27
- 2023TinyML: Tools, Applications, Challenges, and Future Research Directionscited by 14
- 2021Leaky Nets: Recovering Embedded Neural Network Models and Inputs through Simple Power and Timing Side-Channels -- Attacks and Defensescited by 11
- 2021WaNet -- Imperceptible Warping-based Backdoor Attackcited by 5
- 2022Machine Learning Sensorscited by 5
- 2023Benchmarking Adversarial Robustness of Compressed Deep Learning Modelscited by 3
- 2024Materiality and Risk in the Age of Pervasive AI Sensorscited by 2
- 2024Enhancing TinyML Security: Study of Adversarial Attack Transferabilitycited by 2
- 2022Circumventing Backdoor Defenses That Are Based on Latent Separabilitycited by 1
- 2023Datasheets for Machine Learning Sensorscited by 1
- 2024An Empirical Study of the Influence of Adversarial Fine-Tuning on Compressed Neural Networkscited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.