FIELD: information technologies.
SUBSTANCE: invention relates to the field of computer security. Classifier computer training system for determining whether the target object poses the computer security threat, contains the hardware processor and the memory device, wherein the hardware processor is configured to use the trained classifiers cascade to determine whether the target object poses the computer security threat, at that, the classifiers cascade is trained on the training records array, wherein the training array is pre-classified into at least the first class and the second class of records, in response to the training classifiers, the records set deletion from the training array for the reduced training array development.
EFFECT: enabling the training data large volumes fast processing, with the false operations minimum percentage.
21 cl, 17 dwg
Title | Year | Author | Number |
---|---|---|---|
COMPUTER SYSTEM AND METHOD FOR DETECTING MALWARE USING MACHINE LEARNING | 2021 |
|
RU2802860C1 |
SYSTEM AND METHOD FOR TWO-STAGE CLASSIFICATION OF FILES | 2018 |
|
RU2708356C1 |
SYSTEMS AND METHODS FOR DETECTING BEHAVIOURAL THREATS | 2019 |
|
RU2778630C1 |
CLASSIFICATION OF DOCUMENTS USING MULTILEVEL SIGNATURE TEXT | 2014 |
|
RU2632408C2 |
SYSTEMS AND METHODS FOR DETECTING BEHAVIOURAL THREATS | 2019 |
|
RU2803399C2 |
METHOD AND SYSTEM FOR SEARCHING FOR SIMILAR MALWARE BASED ON RESULTS OF THEIR DYNAMIC ANALYSIS | 2020 |
|
RU2738344C1 |
METHODS AND SERVERS FOR DETERMINING METRIC-DEPENDENT THRESHOLDS USED WITH MULTIPLE NESTED METRICS FOR BINARY CLASSIFICATION OF A DIGITAL OBJECT | 2020 |
|
RU2795202C2 |
SYSTEMS AND METHODS FOR DETECTING BEHAVIOURAL THREATS | 2019 |
|
RU2772549C1 |
ELIMINATION OF FALSE ACTIVATION OF ANTI-VIRUS RECORDS | 2016 |
|
RU2625053C1 |
SYSTEMS AND METHODS FOR TRANSLATING NATURAL LANGUAGE SENTENCES INTO DATABASE QUERIES | 2019 |
|
RU2792579C2 |
Authors
Dates
2019-02-26—Published
2016-05-07—Filed