all InfoSec news
Neural Networks with (Low-Precision) Polynomial Approximations: New Insights and Techniques for Accuracy Improvement
Feb. 20, 2024, 5:11 a.m. | Chi Zhang, Man Ho Au, Siu Ming Yiu
cs.CR updates on arXiv.org arxiv.org
Abstract: Replacing non-polynomial functions (e.g., non-linear activation functions such as ReLU) in a neural network with their polynomial approximations is a standard practice in privacy-preserving machine learning. The resulting neural network, called polynomial approximation of neural network (PANN) in this paper, is compatible with advanced cryptosystems to enable privacy-preserving model inference. Using ``highly precise'' approximation, state-of-the-art PANN offers similar inference accuracy as the underlying backbone model. However, little is known about the effect of approximation, and …
accuracy arxiv called cs.cr cs.lg functions improvement insights linear low machine machine learning network networks neural network neural networks non practice privacy standard techniques
More from arxiv.org / cs.CR updates on arXiv.org
WAVES: Benchmarking the Robustness of Image Watermarks
25 minutes ago |
arxiv.org
MOAT: Towards Safe BPF Kernel Extension
25 minutes ago |
arxiv.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
Senior Security Researcher - Linux MacOS EDR (Cortex)
@ Palo Alto Networks | Tel Aviv-Yafo, Israel
Sr. Manager, NetSec GTM Programs
@ Palo Alto Networks | Santa Clara, CA, United States
SOC Analyst I
@ Fortress Security Risk Management | Cleveland, OH, United States