Unknown malcode detection using classifiers with optimal training sets
US8776231B2 · kind B2 · utility
14Cited by
2References
2Claims
0Family size
Inventors
Key dates
| Filing date | May 26, 2009 |
| Grant date | Jul 8, 2014 |
| Priority date | — |
| Expiry date | Mar 18, 2032 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for detecting unknown malicious code is provided. A data set is created, which is a collection of files that includes a first subset with malicious code and a second subset with benign code files, whereas the malicious and benign files are identified by an antivirus program. Subsequently, all files are parsed and a set of top features of all-n grams of the files is selected and reduced by using features selection methods. After determining the optimal number of features, they will be used as training and test sets.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.