Showing 2021Show all
3 papers · 1 filter
cs.CR2021
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.…
cs.CR2021
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…
cs.LG2021
Impact of Spatial Frequency Based Constraints on Adversarial Robustness
Rémi Bernhard, Pierre-Alain Moellic, Martial Mermillod +4
Adversarial examples mainly exploit changes to input pixels to which humans are not sensitive to, and arise from the fact that models make decisions based on uninterpretable featur…