Quantile regression analysis method for detecting cyber attacks
US11652843B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 31, 2020 |
| Grant date | May 16, 2023 |
| Priority date | — |
| Expiry date | Jun 9, 2041 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04L63/1433
- WIPO fieldDigital communication
- WIPO sectorElectrical engineering
Abstract
A system and method for detecting cyber-attacks using quantile regression analysis are disclosed. The method includes identifying at least one hit quantile out of a plurality of quantiles, wherein at least one sample of traffic directed at a protected entity falls within quantile edges of the at least one identified hit quantile, wherein each of the plurality of quantiles is characterized by a probability distribution of at least one feature of a data stream, each of the plurality of quantiles having a respective probability estimate of bytes to fall into it; updating the probability estimates of the plurality of quantiles when the hit quantile has been identified; determining if the probability estimate of the at least one hit quantile is above a threshold; and detecting a cyber-attack when the probability estimate of the at least one hit quantile is above the threshold.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.