Date of Award
3-2023
Document Type
Thesis
Degree Name
Master of Science
Department
Department of Electrical and Computer Engineering
First Advisor
James W. Dean, PhD
Abstract
SCA attacks aim to recover some sort of secret information, often in the form of a cipher key, from a target device. Some of these attacks focus on either power-based leakage, or EM-based leakage. Neural networks have recently gained in popularity as tools in SCA attacks. Near-field EM probes with high-spatial resolution enable attackers to isolate physical locations above a processor. This enables attackers to exploit the spatial dependencies of algorithms running on said processor. These spatial dependencies result in different physical locations above a chip emanating different signal strengths. The strengths of different locations can be mapped using the performance of a neural network trained to detect secret information on near-field leakage data. Our contribution uses this mapping to identify ideal near-field leakage collection locations from which to conduct an attack. This paper demonstrates the effectiveness of this technique in reducing the time needed to conduct a successful EM SCA attack.
AFIT Designator
AFIT-ENG-MS-23-M-030
Recommended Citation
Heffron, Ian C., "Characterizing Location-Based Electromagnetic Leakage of Computing Devices using Convolutional Neural Networks to Increase the Effectiveness of Side-Channel Analysis Attacks" (2023). Theses and Dissertations. 6927.
https://scholar.afit.edu/etd/6927
Comments
A 12-month embargo was observed.
Approved for public release. Case number on file.