New Dithered Gaussian Mechanism enhances differential privacy efficiency

Researchers have introduced the Dithered Gaussian Mechanism, a new approach to differential privacy that enhances security and efficiency. This method discretizes the private output rather than the noise distribution, inheriting the privacy guarantees of the standard Gaussian mechanism while mitigating vulnerabilities from finite-precision floating-point outputs. The mechanism is designed to be randomness-efficient, separating high-quality random bits for critical sampling from a public source for discretization, thereby enabling the use of cryptographically secure randomness with minimal performance impact. An application in DP-SGD for model training demonstrates its potential for secure noise generation with reduced floating-point risks and modest overhead. AI

IMPACT Enhances privacy guarantees in machine learning model training by improving noise generation efficiency and security.

RANK_REASON The cluster contains a research paper detailing a new mechanism for differential privacy.

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• CORE Recommender
• DagsHub
• Dithered Gaussian Mechanism
• DP SGD
• Gaussian mechanism
• Gotit.pub
• Hugging Face
• Influence Flower
• ScienceCast

• paper
• safety

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →