Patent · US Active

Machine learning for input fuzzing

US10983853B2 · kind B2 · utility

1Cited by

2References

20Claims

0Family size

Assignee

MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

Patrice Godefroid · Naperville, US
Rishabh Singh · Cambridge, US
Hila Peleg · Nes Ziona, IL

Key dates

Filing date	Jun 30, 2017
Grant date	Apr 20, 2021
Priority date	—
Expiry date	Feb 20, 2040

Classification

Technology area (CPC G)Physics
CPC primaryG06F40/44
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Provided are methods and systems for automatically generating input grammars for grammar-based fuzzing by utilizing machine-learning techniques and sample inputs. Neural-network-based statistical learning techniques are used for the automatic generation of input grammars. Recurrent neural networks are used for learning a statistical input model that is also generative in that the model is used to generate new inputs based on the probability distribution of the learnt model.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.