all InfoSec news
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
April 16, 2024, 4:11 a.m. | Kostadin Garov, Dimitar I. Dimitrov, Nikola Jovanovi\'c, Martin Vechev
cs.CR updates on arXiv.org arxiv.org
Abstract: Malicious server (MS) attacks have enabled the scaling of data stealing in federated learning to large batch sizes and secure aggregation, settings previously considered private. However, many concerns regarding the client-side detectability of MS attacks were raised, questioning their practicality. In this work, for the first time, we thoroughly study client-side detectability. We first demonstrate that all prior MS attacks are detectable by principled checks, and formulate a necessary set of requirements that a practical …
aggregation arxiv attacks batch client client-side cs.cr cs.lg data data stealing federated federated learning large malicious private scaling server settings stealing work
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Senior Security Researcher
@ Microsoft | Redmond, Washington, United States
Sr. Cyber Risk Analyst
@ American Heart Association | Dallas, TX, United States
Cybersecurity Engineer 2/3
@ Scaled Composites, LLC | Mojave, CA, US
Information Security Operations Manager
@ DP World | Charlotte, NC, United States
Sr Cyber Security Engineer I
@ Staples | Framingham, MA, United States
Security Engineer - Heartland (Remote)
@ GuidePoint Security LLC | Remote in the US