IP Library › Granted Patent US 11,288,401
Granted Patent B2
US 11,288,401 · App. 16/567,391 · Granted Mar 29, 2022

System and method of reducing a number of false positives in classification of files

Inventors: Sergey V. Prokudin (Moscow, RU); Alexander S. Chistyakov (Moscow, RU); Alexey M. Romanenko (Moscow, RU)
Assignee: AO Kaspersky Lab
G06F21/64G06F16/137G06F21/565G06F2221/033
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,288,401
App. No.
16/567,391
Granted
Mar 29, 2022
Kind
B2
Abstract

Disclosed herein are systems and methods for reducing a number of false positives in classification of files. In one aspect, an exemplary method comprises, analyzing a file to determine whether or not the file is to be recognized as being malicious, when the file is recognized as being malicious, analyzing the file to detect a false positive outcome, when the false positive outcome is detected, excluding the file from being scanned and calculating a flexible hash of the file, and storing the calculated flexible hash in a database of exceptions.

Claims (52)

1. A method for reducing a number of false positives in classification of files, the method comprising:

analyzing a file to determine whether or not the file is to be recognized as being malicious;

when the file is recognized as being malicious, analyzing the file to detect a false positive outcome;

when the false positive outcome is detected, excluding the file from further determination of whether the file is malicious and calculating a flexible hash of the file;

storing the calculated flexible hash in a database of exceptions; and

determining whether or not other files different from the analyzed file are malicious, wherein the determination of whether or not the other files are malicious is performed on a predetermined number of unique files using a single record that includes at least the calculated flexible hash.

2. The method of claim 1 , wherein the false positive outcome is detected when an identifier of the file matches an identifier of a trusted file.

3. The method of claim 1 , wherein the detection of the false positive outcome for the file comprises:

determining that a digital signature certificate is present for the file, comparing the certificate of the file with certificates of trusted files in a database of trusted files; and

detecting the false positive when a valid certificate with which the file is signed is present in the database of trusted files.

4. The method of claim 1 , further comprising:

recognizing the file excluded from being scanned as being trusted.

5. The method of claim 1 , further comprising:

identifying other files having a flexible hash that matches the flexible hash of the file for which the false positive is detected; and

recognizing the identified other files as being trusted.

6. The method of claim 1 , further comprising:

storing files recognized as being trusted in a database of trusted files accessible by any number of computing systems.

7. A system for reducing a number of false positives in classification of files, comprising:

at least one hardware processor configured to:

analyze a file to determine whether or not the file is to be recognized as being malicious;

when the file is recognized as being malicious, analyze the file to detect a false positive outcome;

when the false positive outcome is detected, exclude the file from further determination of whether the file is malicious and calculate a flexible hash of the file; and

store the calculated flexible hash in a database of exceptions; and

determine whether or not other files different from the analyzed file are malicious, wherein the determination of whether or not the other files are malicious is performed on a predetermined number of unique files using a single record that includes at least the calculated flexible hash.

8. The system of claim 7 , wherein the false positive outcome is detected when an identifier of the file matches an identifier of a trusted file.

9. The system of claim 7 , the configuration for the detection of the false positives outcomes comprises configuration for:

determining that a digital signature certificate is present for the file, comparing the certificate of the file with certificates of trusted files in a database of trusted files; and

detecting the false positive when a valid certificate with which the file is signed is present in the database of trusted files.

10. The system of claim 7 , wherein the processor is further configured to:

recognize the file excluded from being scanned as being trusted.

11. The system of claim 7 , wherein the processor is further configured to:

identify other files having a flexible hash that matches the flexible hash of the file for which the false positive is detected; and

recognize the identified other files as being trusted.

12. The system of claim 7 , wherein the processor is further configured to:

store files recognized as being trusted in a database of trusted files accessible by any number of computing systems.

13. A non-transitory computer readable medium storing thereon computer executable instructions for reducing a number of false positives in classification of files, including instructions for:

analyzing a file to determine whether or not the file is to be recognized as being malicious;

when the file is recognized as being malicious, analyzing the file to detect a false positive outcome;

when the false positive outcome is detected, excluding the file from further determination of whether the file is malicious and calculating a flexible hash of the file;

storing the calculated flexible hash in a database of exceptions; and

determining whether or not other files different from the analyzed file are malicious, wherein the determination of whether or not the other files are malicious is performed on a predetermined number of unique files using a single record that includes at least the calculated flexible hash.

14. The non-transitory computer readable medium of claim 13 , wherein the false positive outcome is detected when an identifier of the file matches an identifier of a trusted file.

15. The non-transitory computer readable medium of claim 13 , the instructions for detection of the false positive outcome for the file include instructions for:

determining that a digital signature certificate is present for the file, comparing the certificate of the file with certificates of trusted files in a database of trusted files; and

detecting the false positive when a valid certificate with which the file is signed is present in the database of trusted files.

16. The non-transitory computer readable medium of claim 13 , wherein the instructions further include instructions for:

recognizing the file excluded from being scanned as being trusted.

17. The non-transitory computer readable medium of claim 13 , wherein the instructions further include instructions for:

identifying other files having a flexible hash that matches the flexible hash of the file for which the false positive is detected; and

recognizing the identified other files as being trusted.

18. The non-transitory computer readable medium of claim 13 , wherein the instructions further include instructions for:

storing files recognized as being trusted in a database of trusted files accessible by any number of computing systems.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 11, 2019
From: PROKUDIN, SERGEY V; CHISTYAKOV, ALEXANDER S; ROMANENKO, ALEXEY M
To: AO KASPERSKY LAB
Reel/Frame 050342/0122 →
Continuity (1)
Related Publication 20210073418A1 · Mar 11, 2021
Cited By (1)
US 12,613,993