Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Convolutional neural network-based side channel attack method and system

A convolutional neural network and side-channel attack technology, applied to biological neural network models, transmission systems, neural architectures, etc., can solve the problems of difficult template matching and low universality, and achieve increased attack efficiency and high universality , the effect of improving the attack success rate

Pending Publication Date: 2022-04-05
成都三零嘉微电子有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiencies of the prior art, the present invention provides a side-channel attack method and system based on a convolutional neural network, which solves the problems of difficult template matching and low universality in the prior art, and improves the attack success rate

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Convolutional neural network-based side channel attack method and system
  • Convolutional neural network-based side channel attack method and system
  • Convolutional neural network-based side channel attack method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as Figure 1 to Figure 4 As shown, the purpose of the present invention is to overcome the inaccurate template construction in the prior art, and to propose a convolutional neural network-based lateral Channel attack method, the convolutional neural network in this method can be adapted according to different energy models to improve the attack success rate.

[0041] In order to achieve the purpose of the above invention, the present invention is based on the side channel attack method of deep learning convolutional neural network, comprising the following steps:

[0042] (1) Energy trace data acquisition;

[0043] The cryptographic algorithm is run on the cryptographic device, the key is unchanged, the plaintext is random, and energy traces are collected at the same time. T sample points are collected for each energy trace, and a total of N energy traces are collected.

[0044] (2) feature point extraction;

[0045] Use normalized inter-class variance (Normaliz...

Embodiment 2

[0065] In this embodiment, the following steps are included:

[0066] Step S1: Acquisition of energy trace data;

[0067] Download the cryptographic algorithm firmware (such as AES) to the cryptographic device. The upper computer sends the fixed key and random plaintext to the encryption device, and the encryption device starts to run the encryption algorithm after receiving the key and plaintext, and returns the ciphertext to the upper computer after one encryption is completed. At the same time, the oscilloscope collects the energy signal generated when the encryption device is encrypted, and transmits the energy signal back to the host computer through the network cable. The host computer packs the received ciphertext, energy signal and previously issued plaintext into an energy trace file. Repeatedly collect 100,000 sets of energy traces, and sample 1200 sample points for each energy trace.

[0068] Step S2: feature point extraction;

[0069] Use Normalized Inter-Class...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the technical field of side channel attacks, and discloses a side channel attack method and system based on a convolutional neural network, and the attack method comprises the following steps: S1, collecting energy trace data; s2, extracting feature points; s3, constructing a data set; s4, constructing a convolutional neural network; s5, model training; s6, model evaluation; and S7, key recovery. The problems that in the prior art, template matching is difficult, and universality is low are solved.

Description

technical field [0001] The invention relates to the technical field of side-channel attacks, in particular to a convolutional neural network-based side-channel attack method and system. Background technique [0002] Side channel attack is a method of attacking the key by using the energy or electromagnetic leaked sensitive information generated by the cryptographic equipment during operation. Side-channel attacks include timing attacks, simple energy / electromagnetic attacks, differential energy / electromagnetic attacks, and template attacks. Among them, the template attack belongs to the attack method with learning. The attacker uses the multivariate normal distribution to describe the characteristics of the energy trace, establishes a template and then uses this characteristic to attack. The key to the template attack is how to build an accurate multivariate noise model, that is, the multivariate variable covariance matrix. In the actual attack, there will be many difficul...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H04L9/00H04L9/08G06N3/04
Inventor 陈大钊朱翔何卫国
Owner 成都三零嘉微电子有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products