Testing method for unknown hobbyhorse based on GPU and Bayesian network inference
A Bayesian network and detection method technology, applied in the field of Trojan horse detection, can solve the problem that static detection technology cannot prevent and counter Trojan horse attacks in time, achieve strong ability to deal with uncertain information, strong applicability, and improve generation efficiency Effect
Active Publication Date: 2018-04-06
SHANDONG ZHONGFU INFORMATION IND +1
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Since the static detection technology cannot prevent and fight against unknown Trojan horse attacks in time, there are certain limitations
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
[0022] In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions protected by the present invention will be clearly and completely described below using specific embodiments and accompanying drawings. Obviously, the implementation described below Examples are only some embodiments of the present invention, but not all embodiments. Based on the embodiments in this patent, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this patent.
[0023] This embodiment provides a detection method based on GPU and Bayesian network reasoning of unknown Trojans, such as figure 1 As shown, the methods include:
[0024] S1, the host identifies the program samples by category according to the index characteristics of the samples, serializes the behavior of the program, and constructs the behavior vector of the program;
[0025] S2, the...
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 testing method for an unknown hobbyhorse based on GPU and Bayesian network inference. According to the invention, the detection of the hobbyhorse is performed by means of theBayesian learning theory based on the GPU-acceleration; the detection model of the unknown hobbyhorse is built by means of the Bayesian network; and the problems of characteristic classification difficulty, probability behavior recognition and so on which are existed in the process of unknown hobbyhorse detection are solved by means of Bayesian network inference. A stronger ability to process uncertainty information and a specific inference mechanism can be provided by expressing the uncertain causality among system programs with the conditional probability through the Bayesian network, and the hobbyhorse characteristics are not required to be defined hardly, therefore, the adaptability is better. The hobbyhorse probability is calculated through the Bayesian model based on the existing program characteristics, and the calculating result is the probability of the hobbyhorse by extracting the behavior in the unknown program, therefore, the polymorphic deformable bodies of the hobbyhorseand the new unknown hobbyhorses can be detected effectively.
Description
technical field [0001] The invention relates to the field of Trojan horse detection, in particular to an unknown Trojan horse detection method based on GPU and Bayesian network reasoning. Background technique [0002] The Internet is playing an increasingly important role in the country's political, economic, cultural and other fields, and cyberspace has developed into the fifth strategic space. However, with the rapid development of the Internet, computer Trojan horses are also constantly applying new technologies and new ways to evolve, and the number and harm of Trojan horses are increasing significantly, which makes the research on Trojan horse detection technology more and more important in theory and practice. [0003] At present, the mainstream Trojan horse detection technology is roughly divided into two categories: static detection technology and dynamic detection technology. Static detection technology mainly builds a feature library by extracting the static featu...
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): H04L29/06G06K9/62
CPCH04L63/145G06F18/24155G06F18/214
Inventor 孙宏跃蒋荣曲志峰
Owner SHANDONG ZHONGFU INFORMATION IND