US 11,816,546 B2
Fairness and output authenticity for secure distributed machine learning
Laurent Y. Gomez, Le Cannet (FR)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Nov. 9, 2022, as Appl. No. 17/983,751.
Application 17/983,751 is a continuation of application No. 16/701,955, filed on Dec. 3, 2019, granted, now 11,507,883.
Prior Publication US 2023/0137724 A1, May 4, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 21/60 (2013.01); G06N 20/00 (2019.01); G06N 3/02 (2006.01)
CPC G06N 20/00 (2019.01) [G06F 21/602 (2013.01); G06N 3/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
a non-transitory computer-readable medium storing instructions that, when executed by at least one processor among the one or more processors, cause the at least one processor to perform operations comprising:
assigning random input and output labels to a logical circuit;
generating a garbled table comprising an encryption of the output labels with their respective inputs as symmetric keys;
sending the garbled table to an evaluator;
generating an output discloser table that maps each randomized output label with a corresponding output value, encrypted with a pre-shared key k;
sending the output discloser table to an output discloser along with the key k;
providing a randomized input label for the evaluator in response to a request from the evaluator;
receiving a randomized output label from the evaluator;
sending a mapping output value to the evaluator;
receiving a matching encrypted output from the output discloser; and
decrypting the matching encrypted output using the key k.