SYSTEM AND METHOD FOR DETECTING COMPUTER SECURITY THREATS BASED ON VERDICTS OF COMPUTER USERS

Patent №

US 8,214,904

Granted

2012-07-03

Filed 2011

Owner

KASPERSKY LAB ZAO

Lab

AI components

2

kr · planning

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

13332975

Disclosed are systems, methods and computer program products for detecting unknown security threats. In one example, a system receives from an antivirus application deployed on a user's computer information about an unknown security event associated with a software executing on the computer and a user's verdict indicating that the software is harmful or clean. The system identifies the user of the computer and a role of the user. The role indicates user's level of expertise in the field of computer security. If the user has a high level of expertise in computer security, the system accepts the user's verdict. If the user has a low level of expertise, the system analyzes the information about the security event to verify that the user's verdict is correct. If the user's verdict was accepted or verified to be correct, the system updates an antivirus database associated with the antivirus application.

Knowledge representationPlanningH04L 63/1416G06F 21/56G06Q 10/00G06Q 10/10H04L 63/1433

AI classification

Planning0.99
Knowledge representation0.99
Vision0.37
Machine learning0.04
Natural language0.01
AI hardware0.01
Evolutionary computation0.00
Speech0.00

Ownership

KASPERSKY LAB ZAO

assignment · 274260659

Assignors

DOUKHVALOV, ANDREY P., TIKHOMIROV, ANTON V.

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC