all InfoSec news
User-Entity Differential Privacy in Learning Natural Language Models. (arXiv:2211.01141v2 [cs.CR] UPDATED)
Nov. 10, 2022, 2:20 a.m. | Phung Lai, NhatHai Phan, Tong Sun, Rajiv Jain, Franck Dernoncourt, Jiuxiang Gu, Nikolaos Barmpalios
cs.CR updates on arXiv.org arxiv.org
In this paper, we introduce a novel concept of user-entity differential
privacy (UeDP) to provide formal privacy protection simultaneously to both
sensitive entities in textual data and data owners in learning natural language
models (NLMs). To preserve UeDP, we developed a novel algorithm, called
UeDP-Alg, optimizing the trade-off between privacy loss and model utility with
a tight sensitivity bound derived from seamlessly combining user and sensitive
entity sampling processes. An extensive theoretical analysis and evaluation
show that our UeDP-Alg outperforms …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Information Security Engineers
@ D. E. Shaw Research | New York City
Deputy Chief Information Security Officer
@ City of Philadelphia | Philadelphia, PA, United States
Global Cybersecurity Expert
@ CMA CGM | Mumbai, IN
Senior Security Operations Engineer
@ EarnIn | Mexico
Cyber Technologist (Sales Engineer)
@ Darktrace | London