# US 2020/0334353 A1 · Method and system for detecting and classifying malware based on families

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0334353 A1
- Document ID: US20200334353A1
- Status: Published application
- Kind: A1
- Application number: 16/387,642
- Filed: 2019-04-18
- Published: 2020-10-22
- Earliest claimed: 2019-04-18
- Assignees: Checkpoint Software Technologies Ltd.
- Applicants: Checkpoint Software Technologies Ltd.
- Inventors: Ivan KOSAREV; Lotem FINKELSTEIN
- Web page: https://patentgrep.com/patent/US20200334353A1

## CPC

- G06F 21/53: by executing in a restricted environment, e.g. sandbox or secure virtual machine
- G06F 21/56: Computer malware detection or handling, e.g. anti-virus arrangements
- G06N 7/02: using fuzzy logic (computing arrangements based on biological models G06N3/00; computing arrangements using knowledge-based models G06N5/00)
- G06F 2221/033: Test or assess software
- G06F 2221/034: Test or assess a computer or a system
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Methods and systems utilizing sandbox outputs for files, such as dynamic file analysis (DFA) reports, regardless of size, to automatically create rules. From these rules, the maliciousness of the file is determined, and if the file is malicious, i.e., malware, the malware is classified into malware families.

## Claims

### Claim 1

A method of using a particular computer to classify malware, comprising:
using the particular computer to represent a report of a sandbox emulation of a file with one or more first fuzzy hashes;
using the particular computer to compare the one or more first fuzzy hashes of the represented report with second fuzzy hashes of one or more files of known malware, to determine malware candidate files; and,
using the particular computer to analyze each said malware candidate file for artifact matches with artifacts extracted from the representation of the sandbox emulation report.

### Claim 2 (depends on 1)

The method of claim 1, wherein the using the particular computer to compare the one or more first fuzzy hashes of the representation of the sandbox emulation report with the second fuzzy hashes of one or more files of known malware includes: using the particular computer to compare the first fuzzy hashes to the second fuzzy hashes in a distance analysis of points on the first and second fuzzy hashes.

### Claim 3 (depends on 2)

The method of claim 2, wherein the particular computer, prior to determining the malware candidate files determines whether the file is malicious or benign from the representation of the sandbox emulation report.

### Claim 4 (depends on 3)

The method of claim 3, wherein the particular computer, having determined that the file is malicious analyzes the comparison of the one or more first fuzzy hashes of the representation of the sandbox emulation report with second fuzzy hashes of one or more files of known malware, to determine zero or more candidate files.

### Claim 5 (depends on 4)

The method of claim 4, wherein when the particular computer determines a predetermined amount of points are within a predetermined distance of each other, the file corresponding to the second fuzzy hash is a malware candidate file.

### Claim 6 (depends on 5)

The method of claim 5, wherein the predetermined amount of points being within a predetermined distance is approximately 70 percent.

### Claim 7 (depends on 4)

The method of claim 4, wherein when there are zero candidate files, the particular computer classifies the file as unknown malware.

### Claim 8 (depends on 4)

The method of claim 4, wherein when there are one or more candidate files, the particular computer analyzes each said malware candidate file for artifact matches with artifacts extracted from the representation of the sandbox emulation report, such that the artifact matches include the artifacts in the candidate malware files matching at least 10 percent of the artifacts extracted from the representation of the sandbox emulation report.

### Claim 9 (depends on 8)

The method of claim 8, wherein when artifact matches are less than approximately 10 percent, the particular computer classifies the malware as new and unknown.

### Claim 10 (depends on 8)

The method of claim 8, wherein when artifact matches are greater than approximately 10 percent, the particular computer classifies the malware as known.

### Claim 11 (depends on 10)

The method of claim 10, wherein the particular computer selects the best fit candidate file from the candidate files with artifact matches greater than approximately 10 percent,

### Claim 12 (depends on 11)

The method of claim 11, wherein the particular computer assigns the best fit candidate file to a known malware family.

### Claim 13 (depends on 8)

The method of claim 8, additionally comprising: extracting artifacts from the representation of the sandbox emulation report, such that the extracted artifacts are used for artifact matching with artifacts in each of the one or more malware candidate files.

### Claim 14 (depends on 1)

The method of claim 1, wherein the sandbox emulation report is approximately 100 Megabytes.

### Claim 15 (depends on 14)

The method of claim 14, wherein the representation of the sandbox emulation report is less than the sandbox emulation report.

### Claim 16 (depends on 15)

The method of claim 15, wherein the representation of the sandbox emulation report is 250 Kilobytes.

### Claim 17

A computer system for classifying malware, comprising:
a non-transitory storage medium for storing computer components; and,
a computerized processor for executing the computer components comprising:
a module for representing a report of a sandbox emulation of a file with one or more first fuzzy hashes;
a module for comparing the one or more first fuzzy hashes of the represented report with second fuzzy hashes of one or more files of known malware, to determine malware candidate files; and,
a module for analyzing each said malware candidate file for artifact matches with artifacts extracted from the representation of the sandbox emulation report.

### Claim 18 (depends on 17)

The computer system of claim 17, additionally comprising:
a module for determining whether the file is malicious or benign from the representation of the sandbox emulation report.

### Claim 19

A computer usable non-transitory storage medium having a computer program embodied thereon for causing a suitably programmed system to classify malware, by performing the following steps when such program is executed on the system, the steps comprising:
representing a report of a sandbox emulation of a file with one or more first fuzzy hashes;
comparing the one or more first fuzzy hashes of the represented report with second fuzzy hashes of one or more files of known malware, to determine malware candidate files; and,
analyzing each said malware candidate file for artifact matches with artifacts extracted from the representation of the sandbox emulation report.

### Claim 20 (depends on 19)

The computer usable non-transitory storage medium of claim 19, wherein the steps additionally comprise: prior to determining the malware candidate files, determining whether the file is malicious or benign from the representation of the sandbox emulation report.
