all InfoSec news
Selective Differential Privacy for Language Modeling. (arXiv:2108.12944v3 [cs.CL] UPDATED)
July 19, 2022, 1:20 a.m. | Weiyan Shi, Aiqi Cui, Evan Li, Ruoxi Jia, Zhou Yu
cs.CR updates on arXiv.org arxiv.org
With the increasing applications of language models, it has become crucial to
protect these models from leaking private information. Previous work has
attempted to tackle this challenge by training RNN-based language models with
differential privacy guarantees. However, applying classical differential
privacy to language models leads to poor model performance as the underlying
privacy notion is over-pessimistic and provides undifferentiated protection for
all tokens in the data. Given that the private information in natural language
is sparse (for example, the bulk …
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
Cybersecurity Triage Analyst
@ Peraton | Linthicum, MD, United States
Associate DevSecOps Engineer
@ LinQuest | Los Angeles, California, United States
DORA Compliance Program Manager
@ Resillion | Brussels, Belgium
Head of Workplace Risk and Compliance
@ Wise | London, United Kingdom