Hardware Trojan detection and discrimination method based on support vector machine

A hardware Trojan detection and support vector machine technology, applied in the direction of internal/peripheral computer component protection, etc., can solve the problems of destroying the original circuit function of the chip, the original circuit cannot work normally, leaking the user's private information, etc., to achieve good detection and low cost , to solve the effect of small samples

Inactive Publication Date: 2018-06-12
TIANJIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF13 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Once the hardware Trojan horse is activated or started, it will destroy the original circuit function of the chip and make the original circuit unable to w

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
  • Hardware Trojan detection and discrimination method based on support vector machine
  • Hardware Trojan detection and discrimination method based on support vector machine
  • Hardware Trojan detection and discrimination method based on support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Embodiments of the present invention are described in further detail below in conjunction with the accompanying drawings:

[0026] A hardware Trojan detection method based on support vector machine. The side channel current signal of the chip circuit is used as the original signal. After normalized data preprocessing, the sample library is divided into a training set and a verification set. The training set is used to train SVM classification The hardware Trojan classification and detection model is generated by the device, and the test set is used to verify the classification prediction accuracy of the model. When the accuracy is not ideal, the K-CV cross-validation method can be used to adjust the training parameters and retrain the SVM classifier to generate a new classification and detection model. , and then verify the accuracy of the classification prediction, and so on, and finally obtain a satisfactory hardware Trojan classification and detection model. Input th...

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 a hardware Trojan detection and discrimination method based on a support vector machine. The method is characterized by comprising the following steps that step 1, bypass signals of a bus chip and a Trojan chip are collected; step 2, normalization preprocessing is carried out on a training dataset and a testing dataset by using normalized mapping; step 3, the training dataset is used to train two classified support vector machine classifiers, and an initial hardware Trojan detection classification model is obtained; step 4, the classification effect of the initial model is verified; step 5, the initial Trojan detection classification model is optimized by using a cross validation method of K-CV; step 6, it is determined whether the to-be-detected chip has a Trojanor not. The method can better solve the practical problems of small sample, nonlinearity, high dimension and the like, the cost of a signal collection and detection platform and other hardware equipment is low, the efficiency and accuracy rate of an algorithm are high, and the detection of the hardware Trojan can be better realized.

Description

technical field [0001] The invention belongs to the technical field of information security and hardware Trojan detection, and relates to a method for detecting and distinguishing a hardware Trojan in an integrated circuit chip, in particular to a method for detecting and distinguishing a hardware Trojan based on a support vector machine. Background technique [0002] A hardware Trojan horse means that an attacker intentionally tampers with a circuit during the design or manufacture of an integrated circuit chip, that is, embeds a redundant circuit with specific functions. Hardware Trojan horses are the main security risks of current information systems. They can exist in the control chip and memory of the system, and intentionally eavesdrop or destroy the data in the system. Once the hardware Trojan horse is activated or started, it will destroy the original circuit function of the chip, making the original circuit unable to work normally; or tamper with the original data i...

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): G06F21/76
CPCG06F21/76
Inventor 苏静张中伟张贤坤王蕊
Owner TIANJIN UNIVERSITY OF SCIENCE AND TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap