all InfoSec news
Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
Feb. 19, 2024, 5:11 a.m. | Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
cs.CR updates on arXiv.org arxiv.org
Abstract: Label smoothing -- using softened labels instead of hard ones -- is a widely adopted regularization method for deep learning, showing diverse benefits such as enhanced generalization and calibration. Its implications for preserving model privacy, however, have remained unexplored. To fill this gap, we investigate the impact of label smoothing on model inversion attacks (MIAs), which aim to generate class-representative samples by exploiting the knowledge encoded in a classifier, thereby inferring sensitive information about its …
arxiv attacks benefits can cs.cr cs.cv cs.lg deep learning hard privacy privacy shield shield
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Social Engineer For Reverse Engineering Exploit Study
@ Independent study | Remote
SITEC- Systems Security Administrator- Camp HM Smith
@ Peraton | Camp H.M. Smith, HI, United States
Cyberspace Intelligence Analyst
@ Peraton | Fort Meade, MD, United States
General Manager, Cybersecurity, Google Public Sector
@ Google | Virginia, USA; United States
Cyber Security Advisor
@ H&M Group | Stockholm, Sweden
Engineering Team Manager – Security Controls
@ H&M Group | Stockholm, Sweden