CPC G06F 11/3624 (2013.01) [G06F 8/30 (2013.01); G06F 8/36 (2013.01); G06F 21/577 (2013.01); G06N 3/0464 (2023.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06N 3/09 (2023.01)] | 20 Claims |
1. A method comprising:
updating a first repository of detected flaws for a software project with a first set of flaws indicated in a first security scan for a first code submission to a software development pipeline;
for the first set of flaws,
obtaining a first set of candidate fixes based, at least partly, on fixes previously implemented for the software project; and
obtaining a second set of candidate fixes from a trained machine learning model pipeline, wherein the trained machine learning model pipeline has been trained with training data based on code submissions of the software project and based on flaw and fix data for other software projects;
presenting at least some of the first and second sets of candidate fixes as suggested fixes for the first set of flaws; and
based on selections from the suggested fixes, supplying training data for ongoing learning of the trained machine learning model pipeline.
|