4 papers
An Overview of Laser Injection against Embedded Neural Network Models
Mathieu Dumont, Pierre-Alain Moellic, Raphael Viera +2
For many IoT domains, Machine Learning and more particularly Deep Learning brings very efficient solutions to handle complex data and perform challenging and mostly critical tasks.…
A Review of Confidentiality Threats Against Embedded Neural Network Models
Raphaël Joud, Pierre-Alain Moellic, Rémi Bernhard +1
Utilization of Machine Learning (ML) algorithms, especially Deep Neural Network (DNN) models, becomes a widely accepted standard in many domains more particularly IoT-based systems…
Luring of transferable adversarial perturbations in the black-box paradigm
Rémi Bernhard, Pierre-Alain Moellic, Jean-Max Dutertre
The growing interest for adversarial examples, i.e. maliciously modified examples which fool a classifier, has resulted in many defenses intended to detect them, render them inoffe…
Impact of Low-bitwidth Quantization on the Adversarial Robustness for Embedded Neural Networks
Rémi Bernhard, Pierre-Alain Moellic, Jean-Max Dutertre
As the will to deploy neural networks models on embedded systems grows, and considering the related memory footprint and energy consumption issues, finding lighter solutions to sto…