US 11,868,768 B2
Detecting secrets in source code
Sean Moran, Putney (GB); Ahmad Emami, New York, NY (US); Fanny Silavong, London (GB); Joachim Fainberg, Oslo (NO); Ashish Tiwari, Glasgow (GB); Antonios Georgiadis, London (GB); Bill Moriarty, West Chester, PA (US); Solomon Olaniyi Adebayo, Glasgow (GB); Georgios Papadopoulos, London (GB); Rohan Saphal, Glasgow (GB); Robert Falconer Keith, Cardross (GB); Rob Otter, Witham (GB); and Stephen Hall, Fordingbridge (GB)
Assigned to JPMORGAN CHASE BANK, N.A., New York, NY (US)
Filed by JPMorgan Chase Bank, N.A., New York, NY (US)
Filed on Sep. 16, 2021, as Appl. No. 17/447,859.
Claims priority of application No. 20210100589 (GR), filed on Sep. 8, 2021.
Prior Publication US 2023/0070420 A1, Mar. 9, 2023
Int. Cl. G06F 8/77 (2018.01); G06F 8/75 (2018.01); G06N 20/00 (2019.01); G06F 8/41 (2018.01); G06F 18/214 (2023.01); G06F 18/21 (2023.01)
CPC G06F 8/77 (2013.01) [G06F 8/427 (2013.01); G06F 8/75 (2013.01); G06F 18/2148 (2023.01); G06F 18/2185 (2023.01); G06N 20/00 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A method for facilitating identification of secrets in source code by using machine learning, the method being implemented by at least one processor, the method comprising:
retrieving, by the at least one processor, a plurality of files from at least one repository, each of the plurality of files including a source code file;
parsing, by the at least one processor, the source code file to identify at least one training feature;
associating, by the at least one processor, a predetermined label with each of the at least one training feature, the predetermined label corresponding to at least one from among a secret label and a non-secret label;
training, by the at least one processor, at least one model by using the at least one training feature and the corresponding predetermined label;
receiving, by the at least one processor via a graphical user interface, at least one test file, the at least one test file including at least one set of source codes;
parsing, by the at least one processor, the at least one set of source codes to identify at least one feature;
determining, by the at least one processor using the at least one model, at least one first characteristic of the at least one feature;
determining, by the at least one processor using the at least one model, at least one second characteristic based on a first attribute of the at least one first characteristic, the at least one second characteristic including at least one from among an obsolete characteristic, a usable characteristic, and a deprecated characteristic; and
determining, by the at least one processor using the at least one model, at least one third characteristic based on a second attribute of the at least one second characteristic, the at least one third characteristic including at least one from among a production characteristic and a development characteristic.