Domain name confrontation sample generation method and device
A technology against samples and domain names, applied in the field of network security, can solve the problems of high labeling cost, long iteration cycle of detection model, poor timeliness and robustness, etc.
Pending Publication Date: 2022-03-08
TSINGHUA UNIV
View PDF0 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the high cost of labeling, it is difficult for the existing DGA detection algorithm to quickly obtain a sufficient amount of the latest DGA domain name training samples, and it is difficult for the model trained on the limited real-world data set to play the expected effect when dealing with the new DGA algorithm. , which makes the iterative cycle of the detection model too long, and the timeliness and robustness of detection are poor
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
[0031] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with aspects of the invention as recited in the appended claims.
[0032] It should be noted that with the continuous development of technology, attackers have begun to design machine learning-based DGA (Domain Generation Algorithm) algorithms to specifically bypass the plagiarism check capabilities of DGA detectors. However, due to the high cost of labeling, it is difficult for the existing DGA detection algorithm to quickly obtain a sufficient amount of the l...
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 relates to a domain name confrontation sample generation method and device, and relates to the field of network security, and the method comprises the steps: obtaining a domain name training sample, and inputting the domain name training sample to a generator, so as to obtain first domain name confrontation data; inputting the first domain name confrontation data into a binary classifier to obtain the authenticity probability of the domain name training sample, and calculating a first loss value according to the authenticity probability and the real data of the domain name training sample; at each moment when the generator generates the first domain name confrontation data character by character, calculating a cross entropy loss value at each moment when the generator generates the first domain name confrontation data character by character by utilizing the language model discriminator and the domain name training sample; training a generator, a binary classifier and a language model discriminator according to the first loss value and the cross entropy loss value at each moment; and in response to a domain name confrontation sample generation request, generating a domain name confrontation sample based on the trained generator. According to the invention, the timeliness and robustness of detection are improved.
Description
technical field [0001] The present disclosure relates to the field of network security, and in particular to a method and device for generating domain name confrontation samples. Background technique [0002] With the continuous development of technology, attackers began to design machine learning-based DGA algorithms to specifically bypass the detection capabilities of DGA detectors. However, due to the high cost of labeling, it is difficult for the existing DGA detection algorithm to quickly obtain a sufficient amount of the latest DGA domain name training samples, and it is difficult for the model trained on the limited real-world data set to play the expected effect when dealing with the new DGA algorithm. , which makes the iterative period of the detection model too long, and the timeliness and robustness of detection are poor. Contents of the invention [0003] In order to overcome the problems existing in related technologies, the present disclosure provides a meth...
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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/047G06N3/045G06F18/214G06F18/2415
Inventor 杨家海方欣孙晓晴王之梁
Owner TSINGHUA UNIV