Generation device, generation method, and generation program
A generation device includes generation circuitry configured to acquire information on software, extract a feature quantity of the software from the information of the software acquired, generate a cluster for each software on the basis of the feature quantity extracted, calculate a clustering result including a center of gravity of the cluster, match the clustering result calculated with the past clustering result when a distance between a center of gravity of a cluster included in the past clustering result calculated from information on malware is equal to or less than a predetermined value, and generate a graph representing a relationship between the software and the malware on the basis of a result of matching.
1 . A generation device comprising:
generation circuitry configured to:
acquire information on software;
extract a feature quantity of the software from the information of the software acquired;
generate a cluster for the software based on the feature quantity extracted, and calculate a clustering result including a center of gravity of the cluster;
match the clustering result calculated with a past clustering result when a distance between a center of gravity of a cluster included in the past clustering result calculated from information on malware is equal to or less than a predetermined value; and
generate a graph representing a relationship between the software and the malware based on a result of matching, and
output the generated graph to a display,
wherein the generation circuitry is further configured to:
acquire information on a plurality of pieces of software in a time series order;
extract an operation or structural characteristic of the software as the feature quantity;
further update the past clustering result;
and connect a node corresponding to the clustering result matched and the node corresponding to the past clustering result by edges in a time series order.
2 . The generation device according to claim 1 , wherein the generation circuitry is further configured to:
extract, as the feature quantity, a permission requested by the software, or a package name and a class name of a source code of the software.
3 . The generation device according to claim 2 , wherein the generation circuitry is further configured to:
generate the cluster using an X-means method;
and match the clustering result using a k-nearest neighbors algorithm.
4 . The generation device according to claim 1 , further comprising:
detection circuitry configured to detect a change in a property of the software; and
distribution circuitry configured to distribute learning data to a machine learning model for identifying software based on the change of the property detected.
5 . A generation method, comprising:
acquiring information on software;
extracting a feature quantity of the software from the information of the software acquired in the acquisition step;
generating a cluster for the software based on the feature quantity extracted, and calculating a clustering result including a center of gravity of the cluster;
matching the clustering result calculated with a past clustering result when a distance between the center of gravity of the cluster included in the past clustering result calculated from information on malware is equal to or less than a predetermined value;
and generating a graph representing the relationship between the software and the malware based on the result of matching, wherein
the acquiring includes acquiring information on a plurality of pieces of software in a time series order,
the extracting includes extracting an operation or structural characteristic of the software as the feature quantity,
the generating of the cluster includes further updating the past clustering result, and
the generating of the graph includes connecting a node corresponding to the clustering result matched and the node corresponding to the past clustering result by edges in a time series order.
6 . A non-transitory computer-readable recording medium storing therein a generation program causing a computer to execute a process comprising:
acquiring information on software;
extracting a feature quantity of the software from the information of the software acquired;
generating a cluster for each of the software based on the feature quantity extracted, and calculating a clustering result including a center of gravity of the cluster;
matching the clustering result calculated with a past clustering result when a distance between a center of gravity of a cluster included in the past clustering result calculated from information on malware is equal to or less than a predetermined value;
and generating a graph representing a relationship between the software and the malware based on a result of matching, wherein
the acquiring includes acquiring information on a plurality of pieces of software in a time series order,
the extracting includes extracting an operation or structural characteristic of the software as the feature quantity,
the generating of the cluster includes further updating the past clustering result, and
the generating of the graph includes connecting a node corresponding to the clustering result matched and the node corresponding to the past clustering result by edges in a time series order.