公开(公告)号：US20230186055A1

公开(公告)日：2023-06-15

申请号：US18081156

申请日：2022-12-14

Applicant: Rensselaer Polytechnic Institute

Inventor： Ge Wang ,  Christopher Wiedeman

IPC: G06N3/0455 ,  G06N3/094

CPC classification number: G06N3/0455 ,  G06N3/094

Abstract: In one embodiment, there is provided a dual neck autoencoder module for reducing adversarial attack transferability. The dual neck autoencoder module includes an encoder module configured to receive input data; a decoder module; and a first bottleneck module and a second bottleneck module coupled, in parallel, between the encoder module and the decoder module. The decoder module is configured to generate a first estimate based, at least in part, on a first intermediate data set from the first bottleneck module, and a second estimate based, at least in part, on a second intermediate data set from the second bottleneck module. The first intermediate data set and the second intermediate data set are at least partially decorrelated based, at least in part, on a correlation loss.