Nearest Neighbor Intrusion Detection Method Based on Perceived Hash Matrix

JIANG Ze-tao; ZHOU Tan-sheng-zi; HAN Li-yao

doi:10.3969/j.issn.0372-2112.2019.07.019

您当前的位置：

首页 >

文章列表页 >

Nearest Neighbor Intrusion Detection Method Based on Perceived Hash Matrix

更新时间：2025-07-16

- Nearest Neighbor Intrusion Detection Method Based on Perceived Hash Matrix
- Acta Electronica Sinica Vol. 47, Issue 7, Pages: 1538-1546(2019)
- 作者机构：
  
  1. 桂林电子科技大学计算机与信息安全学院,广西,桂林,541004
  2. 西北工业大学计算机学院,陕西,西安,710129
  3. 桂林电子科技大学计算机与信息安全学院,广西,桂林,541004
  4. 西北工业大学计算机学院,陕西,西安,710129
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61572147, No.61762066, No.61876049);Science and Technology Project of Guangxi Zhuang Autonomous Region (No.AC16380108);Guangxi Key Laboratory of Image and Graphic and Intelligent Processing (No.GIIP201701, No.GIIP201801, No.GIIP201802, No.GIIP201803);Postgraduate Education Innovation Plan of Guangxi Province (No.2018YJCX46);Natural Science Foundation of Jiangxi Province (No.20171BAB212015)
- DOI：10.3969/j.issn.0372-2112.2019.07.019
  CLC： TP393.08
- Published Online：25 July 2019，
  
  Published：2019
- 稿件说明：
移动端阅览
JIANG Ze-tao, ZHOU Tan-sheng-zi, HAN Li-yao. Nearest Neighbor Intrusion Detection Method Based on Perceived Hash Matrix[J]. Acta Electronica Sinica, 2019, 47(7): 1538-1546.
DOI：

JIANG Ze-tao, ZHOU Tan-sheng-zi, HAN Li-yao. Nearest Neighbor Intrusion Detection Method Based on Perceived Hash Matrix[J]. Acta Electronica Sinica, 2019, 47(7): 1538-1546. DOI： 10.3969/j.issn.0372-2112.2019.07.019.

摘要

针对目前入侵检测效率不高的问题，本文提出一种基于感知哈希矩阵的最近邻入侵检测算法.首先计算训练集中入侵检测对象的感知哈希描述子，并将感知哈希描述子拼接成感知哈希矩阵；然后利用设计好的量化函数对矩阵中的哈希描述子进行量化，并按照感知哈希的性质对矩阵进行约简和调整；在入侵检测阶段用该矩阵快速定位与待检测对象最相近的

个样本，利用

近邻的投票原则完成入侵检测任务.通过理论分析及在KDDCUP99数据集上的相关实验验证了该方法以

（

）的时间复杂度来快速定位最近邻的

个样本，在保持高检测率的同时降低了存储和计算方面的开销，从而更加有效的保护网络环境.

Abstract

In view of the low efficiency of current intrusion detection

this paper proposes a Nearest Neighbor Intrusion Detection algorithm based on Perceptual Hash Matrix. Firstly

the perceptual Hash descriptors of the intrusion detection object in the training set is calculated

and the perceptual Hash descriptors are spliced into a perceptual Hash matrix; Then use the designed quantization function to quantize the Hash digest in the matrix

and reduce and adjust the matrix according to the nature of the perceived Hash. In the intrusion detection phase

the matrix is used to quickly locate

samples closest to the object to be detected

using

nearest neighbors(KNN)'s voting pr

inciples to complete intrusion detection tasks. Theoretical analysis and related experiments on the KDDCUP99 dataset show that the method can quickly locate the nearest neighbor

samples with the

(

) of time complexity

which can reduce the overhead of storage and calculation while maintaining high detection rate

and more effectively protect the network environment.

关键词

Keywords

references

Views

213

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Intrusion Detection Method Based on Capsule Network for Industrial Internet

Intrusion Detection Alert Correlation Based on Choquet Fuzzy Integral

An Alert Correlation and Analysis Algorithm Based on Frequent Pattern Mining

Masquerade Detection Based on Shell Commands and High-Order Markov Chain Models

A Research and Application of Feature Selection Based on KNN and Tabu Search Algorithm in the Intrusion Detection

Related Author

LI Zhi-han

HU Xiang-dong

HU Liang

LI Hong-wei

CHAI Sheng

Nurbol

SUN Jing-ru

WANG Li-na

Related Institution

School of Automation/School of Industrial Internet, Chongqing University of Posts and Telecommunications

Key Laboratory for Symbol Computation and Knowledge Engineering (Jilin University)Ministry of EducationChangchunJilin 130012China

College of Computer Science and Technology Institute,Jilin University

College of Information Science and Engineering,XinJiang University

College of Computer Science and Technology InstituteJilin UniversityChangchunJilin 130012China

⁰