Feb. 7, 2024, 5:10 a.m. | Raphael Joud Pierre-Alain Moellic Simon Pontie Jean-Baptiste Rigaud

cs.CR updates on arXiv.org arxiv.org

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

Director of the Air Force Cyber Technical Center of Excellence (CyTCoE)

@ Air Force Institute of Technology | Dayton, OH, USA

Senior Cyber Security Analyst

@ Valley Water | San Jose, CA

Infosec Engineer II(3-6 Years)

@ MRI Software | Bengaluru, India Office

Cyber Security Analyst

@ ControlUp | Rishon Lezion

Senior Consultant.e (H/F) - Product & Industrial Cybersecurity - CDI

@ Wavestone | Paris, France

Offensive Security Engineer III

@ Fanatics | India - Hyderabad