PulseAugur
EN
LIVE 11:45:49

New algorithm enhances privacy guarantees in selective release machine learning

By PulseAugur Editorial · [3 sources] ·

Researchers have identified a flaw in the privacy accounting of the Differentially Private Selective Update and Release (DPSUR) algorithm. The existing method overlooks variations in sampling probability introduced by its selective release mechanism, potentially weakening privacy guarantees. To address this, a new algorithm called Differentially Private Selective Release based on Clipped Gradients (DPSR-CG) has been proposed, which offers a more rigorous privacy analysis and demonstrates strong performance across various datasets. AI

IMPACT Enhances privacy guarantees for machine learning models trained on sensitive data, potentially enabling wider adoption in regulated industries.

RANK_REASON The cluster contains an academic paper detailing a new algorithm and its analysis.

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

COVERAGE [3]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD

    Machine learning's reliance on sensitive data necessitates privacy-preserving techniques like Differentially Private Stochastic Gradient Descent (DPSGD). However, DPSGD suffers from substantial utility degradation and slow convergence due to gradient clipping and noise injection.…

  2. arXiv stat.ML TIER_1 English(EN) · Xiaobo Huang, Fang Xie ·

    Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD

    arXiv:2606.04384v1 Announce Type: cross Abstract: Machine learning's reliance on sensitive data necessitates privacy-preserving techniques like Differentially Private Stochastic Gradient Descent (DPSGD). However, DPSGD suffers from substantial utility degradation and slow converg…

  3. arXiv stat.ML TIER_1 English(EN) · Fang Xie ·

    Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD

    Machine learning's reliance on sensitive data necessitates privacy-preserving techniques like Differentially Private Stochastic Gradient Descent (DPSGD). However, DPSGD suffers from substantial utility degradation and slow convergence due to gradient clipping and noise injection.…

RELATED ENTITIES

RELATED TOPICS