Privacy Amplification for the Gaussian Mechanism via Bounded Support
arxiv(2024)
摘要
Data-dependent privacy accounting frameworks such as per-instance
differential privacy (pDP) and Fisher information loss (FIL) confer
fine-grained privacy guarantees for individuals in a fixed training dataset.
These guarantees can be desirable compared to vanilla DP in real world settings
as they tightly upper-bound the privacy leakage for a specific
individual in an actual dataset, rather than considering worst-case
datasets. While these frameworks are beginning to gain popularity, to date,
there is a lack of private mechanisms that can fully leverage advantages of
data-dependent accounting. To bridge this gap, we propose simple modifications
of the Gaussian mechanism with bounded support, showing that they amplify
privacy guarantees under data-dependent accounting. Experiments on model
training with DP-SGD show that using bounded support Gaussian mechanisms can
provide a reduction of the pDP bound ϵ by as much as 30
negative effects on model utility.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要