专利检索 ap:("Ahmadreza Mosallanezhad" OR "Ghazaleh Beigi" OR "Huan Liu") AND inv:"Ahmadreza Mosallanezhad" 第 1 页

1.

发明授权
Systems and methods for utility-preserving deep reinforcement learning-based text anonymization 有权

公开(公告)号：US11907666B2

公开(公告)日：2024-02-20

申请号：US17527632

申请日：2021-11-16

申请人： Ahmadreza Mosallanezhad , Ghazaleh Beigi , Huan Liu

发明人： Ahmadreza Mosallanezhad , Ghazaleh Beigi , Huan Liu

IPC分类号： G06F40/30 , G06N20/00 , G06F18/21

CPC分类号： G06F40/30 , G06F18/217 , G06N20/00

摘要： Various embodiments of a system and associated method for anonymization of text without losing semantic utility of text by extracting a latent embedding representation of content with respect to a given task and by learning an optimal strategy for text embedding manipulation to satisfy both privacy and utility requirements are disclosed herein. In particular, the system balances private attribute obfuscation with retained semantic utility.

2.

发明申请
SYSTEMS AND METHODS FOR UTILITY-PRESERVING DEEP REINFORCEMENT LEARNING-BASED TEXT ANONYMIZATION 有权

公开(公告)号：US20220374606A1

公开(公告)日：2022-11-24

申请号：US17527632

申请日：2021-11-16

申请人： Ahmadreza Mosallanezhad , Ghazaleh Beigi , Huan Liu

发明人： Ahmadreza Mosallanezhad , Ghazaleh Beigi , Huan Liu

IPC分类号： G06F40/30 , G06K9/62 , G06N20/00

摘要： Various embodiments of a system and associated method for anonymization of text without losing semantic utility of text by extracting a latent embedding representation of content with respect to a given task and by learning an optimal strategy for text embedding manipulation to satisfy both privacy and utility requirements are disclosed herein. In particular, the system balances private attribute obfuscation with retained semantic utility.