Table of contents

  • This session has been presented May 23, 2025 (11:00 - 12:00).

Description

  • Speaker

    Benoit COQUERET - INRIA, Thales CESTI

With the widespread development of artifical intelligence, Deep Neural Networks (DNN) have become valuable intellectual property (IP). In the past few years, software and hardware-based attacks targetting at the weights of the DNN have been introduced allowing potential attacker to gain access to a near-perfect copy of the victim's model. However, these attacks either fail against more complex architecture or loose in fidelity regarding the targeted model. In this talk, I will present a new attack methodology combining side-channels attacks with software attacks in order to extract more complex DNN.  First, I will present the main methodologies from the state of the art, and the comparison that can be made with traditional cryptanalytic attacks. I will then describe how side-channel attacks can help with the current limitations and introduce our framework as well as our experimental results. This talk will be concluded by the presentation of some potentials future work.

Practical infos

Next sessions

  • Sécurité physique du mécanisme d'encapsulation de clé Classic McEliece

    • March 20, 2026 (10:00 - 11:00)

    • Inria Center of the University of Rennes - Espace de conférences

    Speaker : Brice Colombier - Laboratoire Hubert Curien, Université Jean Monnet, Saint-Étienne

    Le mécanisme d'encapsulation de clé Classic McEliece faisait partie des candidats toujours en lice au dernier tour du processus de standardisation de la cryptographie post-quantique initié par le NIST en 2016. Fondé sur les codes correcteurs d'erreurs, en particulier autour du cryptosystème de Niederreiter, sa sécurité n'a pas été fondamentalement remise en cause. Néanmoins, un aspect important du[…]

    • SemSecuElec

    • Implementation of cryptographic algorithm

  • Double Strike: Breaking Approximation-Based Side-Channel Countermeasures for DNNs

    • March 20, 2026 (11:00 - 12:00)

    • Inria Center of the University of Rennes - Espace de conférences

    Speaker : Lorenzo CASALINO - CentraleSupélec

    Deep neural networks (DNNs) undergo lengthy and expensive training procedures whose outcome - the DNN weights - represents a significant intellectual property asset to protect. Side-channel analysis (SCA) has recently appeared as an effective approach to recover this confidential asset of DNN implementations. Ding et al. (HOST’25) introduced MACPRUNING, a novel SCA countermeasure based on pruning,[…]

    • SemSecuElec

    • Side-channel

  • Protection des processeurs modernes face à la vulnérabilité Spectre

    • April 24, 2026 (10:00 - 11:00)

    • Inria Center of the University of Rennes - Espace de conférences

    Speaker : Herinomena ANDRIANATREHINA - Inria

    Dans la quête permanente d'une puissance de calcul plus rapide, les processeurs modernes utilisent des techniques permettant d'exploiter au maximum leurs ressources. Parmi ces techniques, l'exécution spéculative tente de prédire le résultat des instructions dont l'issue n'est pas encore connue, mais dont dépend la suite du programme. Cela permet au processeur d'éviter d'être inactif. Cependant,[…]

    • SemSecuElec

    • Micro-architectural vulnerabilities

Show previous sessions
Page top