Security chip side channel leak detection method and system based on neural network

Abstract

The invention discloses a safety chip side channel leakage detection method based on a neural network, comprising: for different encryption algorithms, respectively collecting the energy traces of the protection chip and the non-protection chip in the process of executing the encryption algorithm to form a training sample; The processed sample data is marked, and marked according to the encryption algorithm name and protection status; the neural network model is constructed; the constructed neural network model is trained; the trained neural network model is used to calculate the category of the energy trajectory, and the detection result is obtained. Using the neural network can effectively analyze whether there is energy leakage when the encryption device executes the algorithm, with high accuracy and easy expansion, which reduces the skill requirements of testers.

Description

Method and system for detecting side channel leakage of security chip based on neural network technical field The present invention relates to the side channel analysis technology field of chip encryption, specifically relate to a kind of security based on neural network A full-chip side channel leak detection method and system. Background technique [0002] At present, embedded chips are widely used in in-vehicle devices. In-vehicle devices are becoming more and more complex, and the development of the Internet of Vehicles The development has led to more and more attention to its security issues, so security testing has become particularly important. Current testing methods It takes up a lot of manpower, consumes a lot of time for testers, and requires high technical level of testers (for Different encryption methods require different test modules), and a tool that reduces the operation of testers is urgently needed. side channel Energy analysis captures the ener...

AI Technical Summary

Problems solved by technology

The current leak detection algorithms include high-order mask leak detection, mask scheme leak pre-inspection, etc., but at present, there is no detection method that can obtain the conclusion of whether the device has a leak with 100% probability

Images