Cross-device Portability of Machine Learning Models in Electromagnetic Side-Channel Analysis for Forensics

Abstract

The possession of smart devices has ingrained itself into daily life. Therefore, smart devices, such as IoT and smartphones, are crucial sources of evidence in instances where criminal activity occurs. Due to the challenges in traditional digital forensic techniques involving smart devices, it has been recently proposed in the literature to leverage electromagnetic side-channel analysis (EM-SCA) for the purpose. This paper identifies and discusses an important barrier that exists in the application of EM-SCA for digital forensics that hinders its successful use, namely, the issue of cross-device portability of machine learning (ML) models that are used for EM-SCA. Firstly, the paper empirically evaluates the possibility of using trained ML models to extract forensic insights from EM radiation data of IoT devices. During this empirical study, the inability to reuse a trained ML model across different devices is identified. Secondly, the paper surveys the literature in search of related work that has studied the use of EM-SCA to gather information from smart devices. The purpose of the survey is to identify whether any existing work has been able to introduce potential approaches to enable cross-device portability of ML models in EM-SCA. The findings of this survey point to the fact that the identified problem still exists and requires further studies opening the door to future research.

Keywords

• EM-SCA
• cross-device portability
• digital forensic