Anti-scanning method and device based on machine learning Bayesian algorithm, and server
A Bayesian algorithm and machine learning technology, applied in the field of web page security protection, can solve the problems of high false negative rate, data packets occupying network bandwidth, heavy workload, etc., to improve the recognition rate, reduce false negative rate, reduce The effect of testing costs
Inactive Publication Date: 2019-01-15
HANGZHOU ANHENG INFORMATION TECH CO LTD
View PDF5 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] With the development of Internet technology, web application systems have been widely used in government portals, e-commerce, Internet and other industries. However, while facilitating life and work, it also brings hidden dangers to network security.
Hackers use scanning technology to not only find server vulnerabilities to attack, but also a large number of data packets generated by scanning also occupy a large amount of network bandwidth, resulting in the failure of normal network communication
At present, for scanning behavior, it is mainly through simple statistical methods and senior security experts through experience to manually identify scanning behavior. These two methods have a low recognition rate, and in the case of massive access logs, the workload is heavy and the false negative rate is high, so they are not effective. Identify and detect scanning behavior to ensure network security
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
[0024] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. the embodiment. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0025] At present, the traditional webpage security protection method is applied to the webpage server, and the webpage server receives the page access request sent by the target user; if the page link visited by the page access request is a preset fake link, then generate an Camouflage page; where the camouflage link is pre-set to be invisible to normal users of non-scanning devices...
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 an anti-scanning method and device based on a machine learning Bayesian algorithm, and a server, wherein the method is applied to the server and comprises: acquiring the accesslog of a current access behavior of a client; extracting the feature value of the access log from the access log; inputting the feature value into a preset scanning behavior recognition model and outputting a recognition result, wherein the scanning behavior recognition model is obtained by naive Bayesian algorithm model training; if the recognition result indicates that the current access behavior is a scanning behavior, recognizing an IP address corresponding to the current access behavior; and intercepting the access behavior issued from the IP address at a network layer. The method establishes a scanning behavior recognition model by means of the machine learning Bayesian algorithm, recognizes the scanning behavior according to the scanning behavior recognition model, improves the recognition rate of scanning behavior, reduces a missing alarm rate, and reduces the detection cost for the scanning behavior.
Description
technical field [0001] The invention relates to the technical field of webpage security protection, in particular to an anti-scanning method, device and server based on a machine learning Bayesian algorithm. Background technique [0002] With the development of Internet technology, web application systems have been widely used in government portals, e-commerce, Internet and other industries. However, while facilitating life and work, it also brings hidden dangers to network security. Hackers use scanning technology to not only find server vulnerabilities to attack, but also a large number of data packets generated by scanning also occupy a large amount of network bandwidth, resulting in the failure of normal network communication. At present, for scanning behavior, it is mainly through simple statistical methods and senior security experts through experience to manually identify scanning behavior. These two methods have a low recognition rate, and in the case of massive acce...
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 IPC IPC(8): H04L29/06G06N20/00H04L29/12
CPCH04L63/1425H04L63/1466H04L63/1433H04L61/4511
Inventor 唐其彪范渊
Owner HANGZHOU ANHENG INFORMATION TECH CO LTD