公开(公告)号：US20170293772A1

公开(公告)日：2017-10-12

申请号：US15282776

申请日：2016-09-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Rui CHEN ,  Haoran LI ,  Shiva KASIVISWANATHAN ,  Hongxia JIN

IPC: G06F21/62

CPC classification number: G06F21/6245 ,  G06F16/951 ,  G06F21/32 ,  G06F21/6227 ,  G06F21/6254 ,  G06F21/6263 ,  G06F2221/2111 ,  G06Q30/02 ,  G06Q50/01 ,  H04L51/32 ,  H04L63/0407 ,  H04L67/22 ,  H04L67/303 ,  H04L67/306 ,  H04W4/21 ,  H04W12/02 ,  H04W12/08

Abstract: A first device specifies a privacy specification. The privacy specification includes at least a safe zone and a precision parameter may also be specified. A second device, such as an untrusted server, uses the privacy specification to provide guidance to the first device on how to perturb sensitive data. The first device then uses the guidance to transform sensitive data and provides it to the second device. The data transformation permits the first device to share sensitive data in a manner that preserves the privacy of the first user but permits statistics on aggregated data to be generated by an untrusted server.

公开(公告)号：US20230259762A1

公开(公告)日：2023-08-17

申请号：US17972302

申请日：2022-10-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Zhimeng JIANG ,  Kaixiong ZHOU ,  Zirui LIU ,  Li LI ,  Rui CHEN ,  Soo-Hyun CHOI ,  Xia HU

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: An artificial intelligence (AI) classifier is trained using supervised training and an effect of noise in the training data is reduced. The training data includes observed noisy labels. A posterior transition matrix (PTM) is used to minimize, in a statistical sense, a cross entropy between a noisy label and a function of the classifier output. A loss function using the PTM is provided to use in training the classifier. The classifier provides final output predictions with good performance even with the existence of noisy labels. Also, information fusion is included in the classifier training using the PTM and an estimated noise transition matrix (NTM) to reduce estimation error at the classifier output.