Vulnerability detection method and device based on context semantics
A vulnerability detection and context technology, applied in the field of information security applications, can solve the problem of high training cost, and achieve the effect of improving accuracy performance, improving effect, and improving efficiency
Pending Publication Date: 2021-10-29
GUANGDONG POWER GRID CO LTD
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At present, the application research on software vulnerability detection based on bidirectional long short-term memory (Bi-LSTM) network is relatively hot. However, due to the complex context information processing and iterative training mechanism under the network architecture, the training cost is very high.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings.
[0033] The overall process of the vulnerability detection method based on context semantics is as follows: figure 1 As shown, it mainly includes the following steps: (1) symbolize the obtained code segment, and convert the vulnerability characteristics of each code segment into a specific symbolic representation, wherein the same feature is mapped to the same symbolic representation; (2) ) symbol representation is converted into a vector; (3) vector input is based on the source code vulnerability detection model of ELM, and the vulnerability detection is carried out, and the source code vulnerability detection model based on ELM is trained using the training data set in advance, and the model includes an input layer , hidden layer and output layer.
[0034] In the following description, electric power information system, power grid informati...
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
Login to View More Abstract
The invention provides a vulnerability detection method and device based on context semantics. The method comprises the steps of performing symbolic representation on obtained code segments, converting vulnerability features of each code program segment into specific symbolic representation, wherein the same features are mapped to the same symbolic representation; converting the symbolic representation into a vector; inputting the vector into an ELM-based source code vulnerability detection model for vulnerability detection, obtaining the ELM-based source code vulnerability detection model by training a training data set in advance, wherein the model comprises an input layer, a hidden layer and an output layer. According to the invention, the advantage that the neural network automatically extracts complex features is fully utilized, symbolic representation is carried out on the input codes, then the codes are converted into vectors, context semantic information of the codes is reserved, and the detection effect is effectively improved.
Description
technical field [0001] The invention relates to the field of information security applications, in particular to a method and device for detecting vulnerabilities based on context semantics. Background technique [0002] Electric power enterprises are the subject of network security responsibilities. Incorporate network security into the network security production management system of electric power enterprises, and in accordance with the requirements of the national level protection system, strengthen the construction of professional forces for network security level protection in the power industry. Combined with the new situation of electric power production safety and safety guarantee requirements, improve the new security protection scheme of power grid information system. At present, the power information system software is becoming more and more complex, and the software loopholes caused by design defects and implementation errors have become inevitable problems in e...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F21/57G06N3/08H04L29/06
CPCG06F21/577G06N3/08H04L63/1433
Inventor 沈伍强梁哲恒裴求根曾纪钧龙震岳温柏坚张小陆
Owner GUANGDONG POWER GRID CO LTD