1 citations · 2 across the 10 of their papers we have counts for
10 papers
Hardware-Software Co-Design for Float16 On-Device Training on RISC-V Single-Core
Benjamin Hubinet, Pierre-Alain Moellic, Olivier Savry +2
By leveraging standard RISC-V extensions, namely Zfh (scalar float16) and Zvfh (vector float16), this work proposes an open-source framework to enable complete on-device training o…
Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips
Bastien Vuillod, Kevin Hector, Pierre-Alain Moellic +2
Federated Learning (FL) allows a set of clients to collectively train a global model without sharing local training data. Giving the responsibility of the training to decentralized…
Like an Open Book? Read Neural Network Architecture with Simple Power Analysis on 32-bit Microcontrollers
Raphael Joud, Pierre-Alain Moellic, Simon Pontie +1
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 recove…
Fault Injection and Safe-Error Attack for Extraction of Embedded Neural Network Models
Kevin Hector, Pierre-Alain Moellic, Mathieu Dumont +1
Model extraction emerges as a critical security threat with attack vectors exploiting both algorithmic and implementation-based approaches. The main goal of an attacker is to steal…
Evaluation of Parameter-based Attacks against Embedded Neural Networks with Laser Injection
Mathieu Dumont, Kevin Hector, Pierre-Alain Moellic +2
Upcoming certification actions related to the security of machine learning (ML) based systems raise major evaluation challenges that are amplified by the large-scale deployment of…
Evaluation of Convolution Primitives for Embedded Neural Networks on 32-bit Microcontrollers
Baptiste Nguyen, Pierre-Alain Moellic, Sylvain Blayac
Deploying neural networks on constrained hardware platforms such as 32-bit microcontrollers is a challenging task because of the large memory, computing and energy requirements of…
A Practical Introduction to Side-Channel Extraction of Deep Neural Network Parameters
Raphael Joud, Pierre-Alain Moellic, Simon Pontie +1
Model extraction is a major threat for embedded deep neural network models that leverages an extended attack surface. Indeed, by physically accessing a device, an adversary may exp…
A Closer Look at Evaluating the Bit-Flip Attack Against Deep Neural Networks
Kevin Hector, Mathieu Dumont, Pierre-Alain Moellic +1
Deep neural network models are massively deployed on a wide variety of hardware platforms. This results in the appearance of new attack vectors that significantly extend the standa…
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…