Description
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.
Infos pratiques
Prochains exposés
-
Onysis: A secure European SoC FPGA
Orateur : Adrien GRASSEIN - Nanoxplore
Developed in collaboration with the DGA, the Onysis project introduces a European SoC FPGA designed to embed advanced hardware security features. This presentation will provide an overview of the Onysis architecture, focusing specifically on its native mechanisms to protect critical systems. We will detail the implementation of its integrated security subsystem, covering the secure boot sequence[…]-
SemSecuElec
-
-
Using High Level Profiling Data to Early Assess the Fault Tolerance of Complex Digital Components
Orateur : Luc NOIZETTE - Nuclétudes (filiale Ariane group)
This presentation outlines an innovative methodology for estimating the fault tolerance of complex components based on application profiling obtained using a high-level virtual platform. A derating factor, derived exclusively from profiling metrics (e.g., lifetime in memory and registers), is calibrated using a reliability dataset collected from a set of benchmarks. Applying it to test softwares[…]-
SemSecuElec
-
Fault injection
-
-
An Assessment of the Security of Reconfigurable Cloud Computing
Orateur : Russell Tessier - University of Massachusetts
In this talk, we examine efforts to protect network processing and computation in cloud-based FPGAs from hardware- and software-based attacks. FPGAs have served as integral components in cloud computing for a decade, even though commercial FPGA architectures were not designed for cloud deployment. A range of potential attacks on cloud-based FPGAs and their remediations are examined. We[…]-
SemSecuElec
-
-
Securing processor's microarchitecture against SCA in a post-quantum cryptography setting
Orateur : Vincent MIGLIORE - LAAS-CNRS
Hardware microarchitecture is a well-known source of side-channel leakages, providing a notable security reduction of standard cryptographic algorithms (e.g. AES) if not properly addressed by software or hardware. In this talk, we present new design approaches to harden processor's microarchitecture against power-based side-channel attacks, relying on configurable and cascadable building blocks[…]-
SemSecuElec
-
Side-channel
-
Micro-architectural vulnerabilities
-
-
Compositional Semantics for Detection and Defense of Speculative Leaks
Orateur : Xaver Fabian - CISPA Helmholtz Center for Information Security
Speculative execution improves CPU performance but introduces vulnerabilities, known as Spectre attacks, which exploit microarchitectural side effects to leak sensitive data. Modern processors employ multiple interacting speculation mechanisms, yet existing approaches predominantly analyze them in isolation, which limits both the automated detection of complex leaks and the formal verification of[…]-
SemSecuElec
-
Side-channel
-
Micro-architectural vulnerabilities
-