Patent · US Active

Contextual embeddings for improving static analyzer output

US11765193B2 · kind B2 · utility

0Cited by

8References

20Claims

0Family size

Assignee

International Business Machines Corporation · US

Inventors

Saurabh Pujar · White Plains, US
Luca Buratti · White Plains, US
Alessandro Morari · New York, US
Jim A. Laredo · Katonah, US
Mihaela Ancuta Bornea · White Plains, US
Jeffrey Scott McCarley · Mount Kisco, US
Yunhui Zheng · Yorktown Heights, US

Key dates

Filing date	Dec 30, 2020
Grant date	Sep 19, 2023
Priority date	—
Expiry date	Aug 7, 2041

Classification

Technology area (CPC H)Electricity
CPC primaryH04L63/20
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

In a computer-implemented method for improving a static analyzer output, a processor receives a labeled data set with labeled true vulnerabilities and labeled false vulnerabilities. A processor receives pretrained contextual embeddings from a contextual embeddings model. A processor maps the true vulnerabilities and the false vulnerabilities to the pretrained contextual embeddings model. A processor generates a fine-tuned model with classifications for true vulnerabilities.

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