A method of intrusion detection for android platform based on cfsfdp clustering

Abstract

The invention discloses an Android platform intrusion detection method based on CFSFDP clustering, and relates to the field of network information security. The problems that existing static feature detection methods occupy a great number of system resources, existing dynamic feature detection methods have different data sources and model construction methods, detection performance difference of different methods is large, and the like are solved, and static features and dynamic features of an Android platform are collected and captured; static data and dynamic feature data are normalized anddiscretized, normal behavior feature data is obtained, and the normal behavior feature data is calibrated; a CFSFDP algorithm is adopted to cluster the feature data to generate contours; abnormality detection is conducted on the generated behavioral contours, it is determined that whether or not current points are within the cutoff distance of point in the contours, if yes, the behaviors re considered as normal behaviors, otherwise as abnormal behaviors, and the abnormal behaviors push alarms in real time, and feed back current feature status information to a user. The method can reduce the amount of storage of the contours without reducing the contour accuracy.

Description

technical field [0001] The invention relates to the field of network information security, and relates to an Android platform intrusion detection method based on clustering by Fast Search and Find of Density Peaks (CFSFDP Clustering by Fast Search and Find of Density Peaks). Background technique [0002] Intrusion detection method is a common method to protect information security and ensure the normal operation of global information infrastructure, and it is an important research direction in the field of information security. In recent years, with the widespread application of the Android platform and its services, its security issues have also received extensive attention. The security mechanism of the existing Android platform has limitations, and the Android platform intrusion detection is a good supplement and expansion. According to the different data sources, intrusion detection methods on the Android platform can be divided into two categories: static features and ...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems that the existing static feature detection method occupies a large amount of system resources, lacks the ability to detect unknown attacks, the dynamic feature detection method has inconsistent data sources and model construction methods, and the detection performance of different methods is quite different, it provides A kind of Android platform intrusion detection method based on CFSFDP clustering, specifically comprises the following steps:

Images