US 11,861,200 B2
Data block-based system and methods for predictive models
Robert L. Grossman, River Forest, IL (US); Matthew C. Swort, Port Deposit, MD (US); and James E. Heath, Sugarloaf, FL (US)
Assigned to IronNet Cybersecurity, Inc., McLean, VA (US)
Filed by IronNet Cybersecurity, Inc., McLean, VA (US)
Filed on Nov. 18, 2022, as Appl. No. 17/990,601.
Application 17/990,601 is a continuation of application No. 16/855,027, filed on Apr. 22, 2020, granted, now 11,507,291.
Prior Publication US 2023/0095468 A1, Mar. 30, 2023
Int. Cl. H04L 29/06 (2006.01); G06F 3/06 (2006.01); H04L 9/06 (2006.01); G06F 21/62 (2013.01); G06N 5/025 (2023.01)
CPC G06F 3/064 (2013.01) [G06F 3/067 (2013.01); G06F 3/0614 (2013.01); G06F 3/0653 (2013.01); G06F 21/62 (2013.01); G06F 21/6245 (2013.01); G06N 5/025 (2013.01); H04L 9/0637 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for securely storing auditable data comprising:
generating a blockchain ledger comprising a plurality of data blocks comprising a data block encryption header and a data block encrypted payload, wherein the data block encrypted payload comprises a data block header and a data block payload;
generating a plurality of data storage blocks stored in the data block payload of the blockchain ledger, wherein the data storage blocks are used in at least one of building an analytic model and an analytic workflow; and
generating a plurality of data provenance blocks stored in the blockchain ledger, wherein at least one of the plurality of data provenance blocks stores provenance data related to building one of an analytic model and an analytic workflow or related to using one of an analytic model and an analytic workflow to score data and produce outputs;
wherein at least a portion of the data stored in the data storage blocks build an analytic model or an analytic workflow, and at least a portion of the data stored in the data storage blocks score that data, and
wherein at least a portion of the data stored in the data provenance blocks comprises logging data generated as a function of some of the data in the data storage blocks to store an analytic model or workflow and as a function of some of the data in the data storage blocks to score that data using an analytic model or analytic model.