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)
Practical infos
Next sessions
-
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
-
-
Security of Smart Dust: Robust Key Derivation for Single-Chip Systems
Speaker : Sara Faour - Inria
The Smart Dust vision seeks to enable large networks of millimeter-scale wireless sensor nodes that tightly integrate sensing, computation, communication, and power management into a single-chip device. Establishing a robust hardware root of trust for such devices remains challenging, particularly in single, low-cost chip manufacturing processes that lack embedded writable Non-Volatile Memory (NVM[…] -
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
-
-
Onysis: A secure European SoC FPGA
Speaker : 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
-