On the adversarial robustness of full integer quantized TinyML models at the edge
Davy Preuveneers, Willem Verheyen, Sander Joos, Wouter Joosen · 2023
The recent surge in deploying machine learning (ML) models at the edge has revolutionized various industries by enabling real-time decision-making on resource-constrained devices, such as TinyML models on microcontrollers. However, this trend brings forth a critical concern - the vulnerability of these models to adversarial examples. ML at the edge offers tremendous potential but demands heightened vigilance in the realm of cybersecurity.