US 11,921,896 B2
Systems and methods for anonymizing a dataset of biometric data while retaining data utility
Bill Moriarty, West Chester, PA (US); Shaohan Hu, Yorktown Heights, NY (US); Marco Pistoia, Amawalk, NY (US); Hargun Kalsi, Monmouth Junction, NJ (US); Sean Moran, Putney (GB); and Brett Sanford, Tunbridge Wells (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 Nov. 30, 2021, as Appl. No. 17/538,763.
Claims priority of provisional application 63/138,951, filed on Jan. 19, 2021.
Claims priority of provisional application 63/126,935, filed on Dec. 17, 2020.
Prior Publication US 2022/0198061 A1, Jun. 23, 2022
Int. Cl. G06F 21/62 (2013.01); G06F 16/23 (2019.01)
CPC G06F 21/6254 (2013.01) [G06F 16/2379 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A global partitioning-based method for anonymizing a dataset of biometric data, comprising:
receiving, by an anonymization computer program, a value k representing a number of records to hide a biometric datum among, a value t that represents a t-closeness parameter for a t-close distribution, a weight parameter, and a first number of features to retain for determining an attribute of interest;
receiving, by the anonymization computer program, the attribute of interest;
calculating, by the anonymization computer program, a distribution of the attribute of interest in a biometric dataset;
splitting, by the anonymization computer program, the biometric dataset into a plurality of k-sized clusters that satisfy the t-close distribution;
anonymizing, by the anonymization computer program, each biometric datum in the plurality of k-sized clusters using a weighted average of landmarks for the biometric datums in k-sized clusters using the weight parameter;
adding, by the anonymization computer program, each anonymized biometric datum into an anonymized biometric dataset; and
persisting, by the anonymization computer program, the anonymized biometric dataset.