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

Control flow integrity detection method based on deep learning

A technology of integrity detection and deep learning, which is applied in the field of computer security, can solve problems such as large space overhead, and achieve the effects of convenient implementation, high reliability, and high detection accuracy

Pending Publication Date: 2020-06-12
HUNAN FIRST NORMAL UNIV
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the hardware-assisted defense mechanism also needs to expand the instruction set, modify the compiler, and require a large space overhead

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
  • Control flow integrity detection method based on deep learning
  • Control flow integrity detection method based on deep learning
  • Control flow integrity detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention assumes that the system has deployed basic defense mechanisms such as DEP to prevent attackers from injecting malicious codes; the controller can read / write data segments arbitrarily, but can only read / execute code segments; assuming that the application program is credible; however , the attacker buffer overflow and other program vulnerabilities to obtain information on any memory location; in addition, the program cannot dynamically generate code and contain self-changing code, so as to ensure the accuracy of the statically obtained CFG. The above assumptions are suitable for most application scenarios.

[0043] Such as figure 1 Shown is a schematic flow chart of the method of the present invention: the deep learning-based control flow integrity detection method provided by the present invention includes the following steps:

[0044] Training phase:

[0045] S1. Obtain the executable file executable file of the training program;

[0046] S2. D...

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 a control flow integrity detection method based on deep learning. The control flow integrity detection method comprises the steps of obtaining a training program and an executable file thereof; disassembling the executable file and constructing a coarse-grained control flow graph; monitoring a control flow of the program and collecting address information; constructing a fine-grained control flow graph of the training program and segmenting the fine-grained control flow graph to obtain training data; training a classifier to obtain a control flow integrity detection classifier; obtaining address information of a to-be-detected program; constructing a gadget chain code of the program to be detected; and adopting the control flow integrity detection classifier to perform detection and complete integrity detection of the control flow of the to-be-detected program. According to the method, an accurate control flow graph is constructed, then the control flow graph issplit for neural network training, branch information is obtained in real time when a program runs, and detection is carried out through a neural network model; according to the invention, program control flow integrity detection can be well carried out, the reliability is high, the detection accuracy is high, and the implementation is convenient.

Description

technical field [0001] The invention belongs to the field of computer security, and in particular relates to a control flow integrity detection method based on deep learning. Background technique [0002] With the development of economy and technology and the improvement of people's living standards, computers have been widely used in people's production and life, bringing endless convenience to people's production and life. With the advent of the era of intelligence and big data, people are paying more and more attention to computer security issues. [0003] The use of unsafe systems programming languages, such as C and C++, can lead to a large number of vulnerabilities in software. According to a recent security threat report, the number of vulnerabilities has shown a clear upward trend in the past 10 years. [0004] Code reuse attacks (such as ROP and JOP) use memory overflow vulnerabilities to hijack program control flow by using branch instructions in the program with...

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): G06F21/56G06F8/36G06N3/04G06N3/08
CPCG06F21/562G06F8/36G06N3/084G06N3/045
Inventor 王湘奇张吉良
Owner HUNAN FIRST NORMAL UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com