Description
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, a performance-oriented Approximate Computing technique: at inference time, the implementation randomly prunes (or skips) non-important weights (i.e., with low contribution to the DNN’s accuracy) of the first layer, exponentially increasing the side-channel resilience of the protected DNN implementation.
In this presentation, we describe a preprocessing methodology taking advantage of a control-flow dependency intrinsic to the countermeasure's design.
Through practical experiments, we demonstrate the effectiveness of our methodology, recovering up to 96% of the important weights of a MACPruning-protected Multi-Layer Perceptron.
Moreover, we show how microarchitectural leakage improves the effectiveness of our methodology, even allowing for the recovery of up to 100% of the targeted non-important weights.
Lastly, by adapting our methodology, we elaborate on how the pruning mechanism, which depends on the importance of the weights, enables the circumvention of a control-flow-free MACPRUNING implementation.
With this last point, we identify the pruning mechanism underlying MACPRUNING as the root of the countermeasure’s vulnerability.
Autre
Présentation en Anglais (slides en Anglais)
Talk in English (slides in English)
Next sessions
-
Protection des processeurs modernes face à la vulnérabilité Spectre
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
-
-
Post-Quantum Cryptography Accelerated by a Superscalar RISC-V Processor
Speaker : Côme Allart - Inria
Two major changes are currently taking place in the embedded processor ecosystem: open source with the RISC-V instruction set, which could replace the ARM one, and post-quantum cryptography (PQC), which could replace classic asymmetric cryptography algorithms to resist quantum computers.In this context, this thesis investigates the improvement of embedded processor performance, generally for[…]-
SemSecuElec
-
Implementation of cryptographic algorithm
-
-
Chamois: Formally verified compilation for optimisation and security
Speaker : David MONNIAUX - CNRS - Verimag
Embedded programs (including those on smart cards) are often developed in C and then compiled for the embedded processor. Sometimes they are modified by hand to incorporate countermeasures (fault attacks, etc.), but care must be taken to ensure that this does not disrupt normal program execution and that the countermeasure is actually adequate for blocking the attacks.In the process, it is[…]-
SemSecuElec
-
Fault injection
-
Formal methods
-
-
Securing processor's microarchitecture against SCA in a post-quantum cryptography setting
Speaker : 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
-