Open AccessA Hierarchical Approach for Multiple Periodicity Detection in Software Code Analysis
Author(s) -
Mine Kerpicci,
Milos Prvulovic,
Alenka Zajic
Publication year - 2022
Publication title -
ieee access
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.587
H-Index - 127
ISSN - 2169-3536
DOI - 10.1109/access.2022.3212401
Subject(s) - aerospace , bioengineering , communication, networking and broadcast technologies , components, circuits, devices and systems , computing and processing , engineered materials, dielectrics and plasmas , engineering profession , fields, waves and electromagnetics , general topics for engineers , geoscience , nuclear engineering , photonics and electrooptics , power, energy and industry applications , robotics and control systems , signal processing and analysis , transportation
This paper introduces an end-to-end processing method for multiple periodicity signal detection and analysis with particular application in software analysis using analog side channels. The probabilistic distributions of signal blocks are estimated with kernel density estimation. The corresponding kernel bandwidths, which are optimally found in a data-driven manner, are used to detect change points. After separating the signal into parts with different behaviors, average magnitude difference function is leveraged iteratively to find the smallest periodic signal sections. To illustrate efficiency of the proposed method, we use EM side-channel signals collected from real-life applications to successfully detect multiple existing periodicities.