	US 12,105,847 B2
	Differentially private variational autoencoders for data obfuscation
Benjamin Weggenmann, Karlsruhe (DE); Martin Haerterich, Wiesloch (DE); and Florian Knoerzer, Karlsruhe (DE)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Dec. 14, 2021, as Appl. No. 17/550,634.
Prior Publication US 2023/0185962 A1, Jun. 15, 2023
Int. Cl. G06F 21/62 (2013.01)

CPC G06F 21/6254 (2013.01)

20 Claims

1. A computer-implemented method performed by a computer system having a memory and at least one hardware processor, the computer-implemented method comprising:

encoding input data into a latent space representation of the input data, the encoding of the input data comprising:

inferring latent space parameters of a latent space distribution based on the input data, the latent space parameters comprising a mean and a standard deviation, the inferring of the latent space parameters comprising bounding the mean within a finite space and using a global value for the standard deviation, the bounding of the mean within the finite space using a hyperbolic tangent or a stereographic projection, and the global value being independent of the input data; and

sampling data from the latent space distribution; and

decoding the sampled data of the latent space representation into output data.