Web: http://arxiv.org/abs/2210.00053

Nov. 24, 2022, 2:10 a.m. | Reza Nasirigerdeh, Javad Torkzadehmahani, Daniel Rueckert, Georgios Kaissis

cs.CR updates on arXiv.org arxiv.org

Normalization is an important but understudied challenge in privacy-related
application domains such as federated learning (FL), differential privacy (DP),
and differentially private federated learning (DP-FL). While the unsuitability
of batch normalization for these domains has already been shown, the impact of
other normalization methods on the performance of federated or differentially
private models is not well-known. To address this, we draw a performance
comparison among layer normalization (LayerNorm), group normalization
(GroupNorm), and the recently proposed kernel normalization (KernelNorm) in FL, …

kernel machine machine learning networks privacy

Senior Cloud Security Engineer

@ HelloFresh | Berlin, Germany

Senior Security Engineer

@ Reverb | Remote, US

I.S. Security Analyst

@ YVFWC | Yakima, WA

Senior Information Security Analyst (SOC L3)

@ Eurofins | Heredia, Costa Rica

Threat Operations Analyst I, Weekend Shift

@ Huntress | Remote UK

People Lead (Security Engineering)

@ Xero | Wellington, NZ

Senior Threat Intelligence Analyst

@ Kasada | Sydney

Network Security Engineer

@ Cloudflare, Inc. | London, UK

Counter Hybrid and CYBER Threats Advisor (32)

@ EMW, Inc. | Norfolk, Virginia, United States

Joint SOF Trainer (Cyber) IV

@ WWC Global | Tampa, Florida, United States

Privacy Manager

@ MyRepublic | Singapore, Singapore

Penetration Tester

@ SecurityScorecard | Remote