Recurrent neural networks for malware analysis
US9495633B2 · kind B2 · utility
5Cited by
14References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jul 1, 2015 |
| Grant date | Nov 15, 2016 |
| Priority date | — |
| Expiry date | Jul 1, 2035 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/09
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Using a recurrent neural network (RNN) that has been trained to a satisfactory level of performance, highly discriminative features can be extracted by running a sample through the RNN, and then extracting a final hidden state hi, where i is the number of instructions of the sample. This resulting feature vector may then be concatenated with the other hand-engineered features, and a larger classifier may then be trained on hand-engineered as well as automatically determined features. Related apparatus, systems, techniques and articles are also described.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.