TraceFormer: A Transformer-Based Method for Weight Extraction from AIMC Tiles

Euromicro Conference on Digital System Design (DSD), pp. 635–642

Abstract

AnalogIn-Memory Computing (AIMC) has emerged as a promising solution to address the performance and energy efficiency limitations of conventional von Neumann architectures for machine learning (ML) applications. This promising approach relies on analog-to-digital converters (ADCs) to enable the integration of AIMC tiles into larger digital systems. In this paper, we investigate the vulnerability of AIMC tiles to power side-channel attacks targeting these ADCs. Specifically, we demonstrate that the numerical values of weights stored in an AIMC tile, that are often a critical asset of an ML model, can be extracted by analyzing the power consumption of the ADCs. With this objective in mind, we propose TraceFormer, which is a two-phase method: 1) we train a Transformer neural network (NN) model to translate captured ADC power traces into digital output values; 2) we utilize a novel input-controlled weight isolation technique in order to isolate each individual weight within the AIMC tile, and then reveal the isolated weight’s value by ADC power side-channel analysis using the Transformer NN model. We demonstrate the practical applicability and robustness of our proposed method by power side-channel analysis of Oscillator-based ADCs that are typically integrated within AIMC tiles. The experimental results show high accuracy and robustness of our Transformer-based analysis, implying potential vulnerabilities in AIMC tiles.

Authors 4

1. Roozbeh Siyadatzadeh Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden University,Leiden Institute of Advanced Computer Science (LIACS),The Netherlands

2. Fatemeh Mehrafrooz Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden University,Leiden Institute of Advanced Computer Science (LIACS),The Netherlands

3. Nele Mentens Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden University,Leiden Institute of Advanced Computer Science (LIACS),The Netherlands

4. Todor P. Stefanov Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden University,Leiden Institute of Advanced Computer Science (LIACS),The Netherlands