Table of contents

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

  • Date

    March 28, 2025 (10:00 - 11:00)
  • Location

    Inria Center of the University of Rennes Espace de conférences
    Locate on Google Maps
  • Suggest a presentation

  • Add this presentation to my calendar

Next sessions

  • Hardware Trojan Horses and Microarchitectural Side-Channel Attacks: Detection and Mitigation via Hardware-based
    Methodologies

    • January 24, 2025 (10:00 - 11:00)

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

    Speaker : Alessandro PALUMBO - CentraleSupélec, IRISA, Inria

    Hardware Trojan Horses that are software-exploitable can be inserted into microprocessors, allowing attackers to run unauthorized code or escalate privileges. Additionally, it has been demonstrated that attackers could observe certain microprocessor features - seemingly unrelated to the program's execution - to exfiltrate secrets or private data. So, even devices produced in secure foundries could[…]
    • SemSecuElec

    • Side-channel

    • Micro-architectural vulnerabilities

    • Hardware trojan

  • I know what your compiler did: Optimization Effects on Power Side-Channel Leakage for RISC-V

    • January 24, 2025 (11:00 - 12:00)

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

    Speaker : Ileana Buhan - Radboud University Nijmegen

    With the growing prevalence of software-based cryptographic implementations in high-level languages, understanding the role of architectural and micro-architectural components in side-channel security is critical. The role of compilers in case of software implementations towards contribution to side-channel leaks is not investigated. While timing-based side-channel leakage due to compiler effects[…]
    • SemSecuElec

    • Side-channel

  • Covert Communication Channels Based On Hardware Trojans: Open-Source Dataset and AI-Based Detection

    • February 28, 2025 (10:00 - 11:00)

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

    Speaker : Alan Díaz Rizo - Sorbonne Université Lip6

    The threat of Hardware Trojan-based Covert Channels (HT-CCs) presents a significant challenge to the security of wireless communications. In this work, we generate in hardware and make open-source a dataset for various HT-CC scenarios. The dataset represents transmissions from a HT-infected RF transceiver hiding a CC that leaks information. It encompasses a wide range of signal impairments, noise[…]
    • SemSecuElec

    • Machine learning

    • Hardware trojan

  • Measurement the thermal component of clock jitter used as entropy source by TRNGs

    • February 28, 2025 (11:00 - 12:00)

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

    Speaker : Arturo GARAY - STMicroelectronics

    Introduction Measuring the thermal component of clock jitter as an entropy source for True Random Number Generators (TRNGs) is compulsory for the security and evaluation of clock-jitter based TRNGs. However, identifying and isolating the local thermal noise component from other noise sources, particularly flicker noise, while performing a precise measurement remains a challenge. Current[…]
    • SemSecuElec

    • TRNG

Show previous sessions