Energy trace preprocessing method based on Sinc convolution noise reduction auto-encoder

Abstract

The invention discloses an energy trace preprocessing method based on a Sinc convolution noise reduction auto-encoder, and the method comprises the steps of designing a Sinc filter through employing aSinc function, enabling the Sinc filter to serve as a filter of a convolution layer, and obtaining a Sinc convolution layer; constructing a Sinc convolution noise reduction auto-encoder based on theSinc convolution layer; training the Sinc convolution noise reduction auto-encoder by using a data set formed by noise-containing energy trace and clean energy trace sample pairs; and inputting a to-be-processed energy trace into the trained Sinc convolution noise reduction auto-encoder to obtain a preprocessed energy trace. When the method is used for preprocessing the energy trace, the signal-to-noise ratio of the energy trace and the key operation intermediate value is improved by more than 4 times, the correlation is further improved, the efficiency of side channel attack is improved, andthe number of energy traces required by successful side channel attack is reduced.

Description

technical field [0001] The invention relates to the technical field of cryptography, in particular to an energy trace preprocessing method based on a Sinc convolution denoising autoencoder. Background technique [0002] In recent years, with the development of computer technologies such as mobile Internet, cloud computing, and artificial intelligence, we have gradually entered an intelligent information society, and various Internet of Things devices and embedded devices have become part of our lives. In order to ensure information security, these devices have applied cryptography technology, and any cryptography technology is facing the threat of password attacks. Side-channel attack is a powerful attack method for cracking cryptographic algorithms. Attackers collect side-channel information such as time, power consumption, electromagnetic radiation, sound, and heat when cryptographic algorithms run on cryptographic devices, and analyze these information and passwords. The...

AI Technical Summary

Problems solved by technology

However, in the existing research work, there are not many energy trace preprocessing methods based on convolutional neural networks.

In addition, the current energy trace preprocessing scheme based on convolutional neural network mainly focuses on the time domain information of the energy trace, and does not utilize the frequency domain information of the energy trace.

Images