Like an Open Book? Read Neural Network Architecture with Simple Power Analysis on 32-bit Microcontrollers

Model extraction is a growing concern for the security of AI systems. For deep neural network models, the architecture is the most important information an adversary aims to recover. Being a sequence of repeated computation blocks, neural network models deployed on edge-devices will generate distinctive side-channel leakages. The latter can be exploited to extract critical information when targeted platforms are physically accessible. By combining theoretical knowledge about deep learning practices and analysis of a widespread implementation library (ARM CMSIS-NN), our …

adversary analysis architecture book computation cs.ai cs.cr cs.lg devices edge extraction important information microcontrollers model extraction network neural network power recover security simple systems