all InfoSec news
Regularized PolyKervNets: Optimizing Expressiveness and Efficiency for Private Inference in Deep Neural Networks
Dec. 15, 2023, 1:36 a.m. |
IACR News www.iacr.org
ePrint Report: Regularized PolyKervNets: Optimizing Expressiveness and Efficiency for Private Inference in Deep Neural Networks
Toluwani Aremu
Private computation of nonlinear functions, such as Rectified Linear Units (ReLUs) and max-pooling operations, in deep neural networks (DNNs) poses significant challenges in terms of storage, bandwidth, and time consumption. To address these challenges, there has been a growing interest in utilizing privacy-preserving techniques that leverage polynomial activation functions and kernelized convolutions as alternatives to traditional ReLUs. However, these alternative approaches often suffer …
bandwidth challenges computation efficiency eprint report functions linear networks neural networks operations private report storage terms
More from www.iacr.org / IACR News
Post-Doc in Lattice-Based Cryptography
1 day, 16 hours ago |
www.iacr.org
WPEC 2024: NIST Workshop on Privacy Enhancing Cryptography
1 day, 16 hours ago |
www.iacr.org
Indistinguishability Obfuscation from Bilinear Maps and LPN Variants
1 day, 20 hours ago |
www.iacr.org
Securing the Future of GenAI: Policy and Technology
1 day, 20 hours ago |
www.iacr.org
Jobs in InfoSec / Cybersecurity
CyberSOC Technical Lead
@ Integrity360 | Sandyford, Dublin, Ireland
Cyber Security Strategy Consultant
@ Capco | New York City
Cyber Security Senior Consultant
@ Capco | Chicago, IL
Sr. Product Manager
@ MixMode | Remote, US
Corporate Intern - Information Security (Year Round)
@ Associated Bank | US WI Remote
Senior Offensive Security Engineer
@ CoStar Group | US-DC Washington, DC