Bot process detecting and classifying method combining with dynamic and static characteristics

A technology of bots and static features, applied in the field of information security, can solve the problems of low efficiency, long time, and difficulty in solving a large number of bots, so as to reduce the requirements and improve the correctness.

Active Publication Date: 2018-03-23
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] Currently, manual reverse engineering is mainly used for family classification of bot programs. This method is not only time-consuming and inefficie...

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
  • Bot process detecting and classifying method combining with dynamic and static characteristics
  • Bot process detecting and classifying method combining with dynamic and static characteristics
  • Bot process detecting and classifying method combining with dynamic and static characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0039] The invention provides a bot detection and classification method combining dynamic and static features, such as figure 1 shown, including the following steps:

[0040] Step 1: Bot detection

[0041] Bots can be distinguished from other malicious codes by using opcode (a machine code used to describe a certain operation in machine language), PE (Portable Execution) section information and DLL (Dynamic Link Library) sequence. Static detection has the advantages of high security and high detection efficiency. The feature selection in the detection process adopts the optimized TF-IDF-GF algorithm.

[0042] The main process is as follows:

[0043] The core idea of ​​TF-IDF is that the importance of a feature item increases with the number of times it appears in the file, but at the same time it decreases with the frequency of its appearance in the fe...

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 discloses bot process detecting and classifying method combining with dynamic and static characteristics. Bot process detection is performed based on static characteristic information; an improved TF-IDF algorithm is adopted for characteristic selection in the detecting process, wherein the improved TF-IDF algorithm is that a category distinction degree factor GF is added when a TF-IDF weight is calculated through a TF-IDF algorithm and is used for representing the ratio of the appearance degree of characteristic items in a certain category and the appearance degrees of the characteristic items in other categories; detected bot processes run, API sequences and network traffic information during bot process running are extracted, and family classification characteristics of the bot processes are obtained through processing; based on the family classification characteristics of the bot processes, the bot processes are classified. By adopting the bot process detecting and classifying method, automatic classification can be performed, consumed time can be shortened, and the classifying efficiency can be improved.

Description

technical field [0001] The invention relates to the technical field of information security, in particular to a method for detecting and classifying bots combining dynamic and static features. Background technique [0002] A bot is a malicious program that an attacker deploys on an infected computer after intruding into it to complete the attack. By deploying bots on infected computers to form a botnet, attackers can implement various attack methods. [0003] In recent years, the rapid development of IoT technology has enabled network attackers to target IoT devices, and bots parasitic on IoT devices have begun to appear in large numbers. The advancement of cloud computing technology has accelerated the development of bots. Attackers only need to apply for virtual machine resources at a very low cost in the cloud, and they can use these resources to quickly build botnets, making it cheaper and faster to launch botnet attacks. Some attackers use illegally stolen credit card...

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): G06F21/56G06K9/62
CPCG06F21/562G06F21/566G06F2221/033G06F18/2115G06F18/24
Inventor 薛静锋张继郭宇单纯刘康
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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