Extracting Weights of CIM-Based Neural Networks Through Power Analysis of Adder-Trees

Conference Paper (2024)
Author(s)

F.J. Mir (TU Delft - Computer Engineering)

Abdullah Aljuffri (TU Delft - Computer Engineering)

Said Hamdioui (TU Delft - Computer Engineering)

Mottaqiallah Taouil (TU Delft - Computer Engineering)

Research Group
Computer Engineering
DOI related publication
https://doi.org/10.1109/ets61313.2024.10567473
More Info
expand_more
Publication Year
2024
Language
English
Research Group
Computer Engineering
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. @en
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Computation-in-Memory (CIM) architectures present a promising solution for efficient implementation of Neural Networks. Particularly, SRAM-based digital CIM architectures are optimal candidates to realize them. Recent studies have revealed potential weaknesses in these architectures, particularly against power attacks. This study introduces a novel attack method enabling weight extraction through the analysis of the adder tree component within the architecture. In our attack, the k-means clustering technique is employed to identify the hamming weights of the CIM weights. Subsequently, we correlate traces belonging to known weights with traces belonging to Hamming groups with unknown weights in order to identify their weight values. As a case study, the attack was applied on SRAM CIM implementation based on 40nm TSMC technology. The results indicate that the weights stored in the CIM crossbar can be retrieved with 100% accuracy purely by analyzing the power consumption.

Files

Extracting_Weights_of_CIM-Base... (pdf)
(pdf | 1.48 Mb)
- Embargo expired in 23-05-2025
License info not available