all InfoSec news
Data Leakage in Federated Averaging. (arXiv:2206.12395v1 [cs.LG])
June 27, 2022, 1:20 a.m. | Dimitar I. Dimitrov, Mislav Balunović, Nikola Konstantinov, Martin Vechev
cs.CR updates on arXiv.org arxiv.org
Recent attacks have shown that user data can be reconstructed from FedSGD
updates, thus breaking privacy. However, these attacks are of limited practical
relevance as federated learning typically uses the FedAvg algorithm. It is
generally accepted that reconstructing data from FedAvg updates is much harder
than FedSGD as: (i) there are unobserved intermediate weight updates, (ii) the
order of inputs matters, and (iii) the order of labels changes every epoch. In
this work, we propose a new optimization-based attack which …
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
Security Architect - Hardware
@ Intel | IND - Bengaluru
Elastic Consultant
@ Elastic | Spain
OT Cybersecurity Specialist
@ Emerson | Abu Dhabi, United Arab Emirates
Security Operations Program Manager
@ Kaseya | Miami, Florida, United States
Senior Security Operations Engineer
@ Revinate | Vancouver