all InfoSec news
Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data. (arXiv:2109.11429v3 [cs.LG] UPDATED)
June 28, 2022, 1:20 a.m. | Georgi Ganev, Bristena Oprisanu, Emiliano De Cristofaro
cs.CR updates on arXiv.org arxiv.org
Generative models trained with Differential Privacy (DP) can be used to
generate synthetic data while minimizing privacy risks. We analyze the impact
of DP on these models vis-a-vis underrepresented classes/subgroups of data,
specifically, studying: 1) the size of classes/subgroups in the synthetic data,
and 2) the accuracy of classification tasks run on them. We also evaluate the
effect of various levels of imbalance and privacy budgets. Our analysis uses
three state-of-the-art DP models (PrivBayes, DP-WGAN, and PATE-GAN) and shows
that …
data differential privacy impact lg privacy robin synthetic data
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
IAM Engineer - SailPoint IIQ
@ IDMWORKS | Remote USA
Manager, Network Security
@ NFL | New York City, United States
Engineering Team Manager – Security Controls
@ H&M Group | Stockholm, Sweden
Senior Security Consultant
@ LRQA | USA, US