paper-with-me

홈 › Papers

Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions

2023-09-15 · Alycia N. Carey, Minh-Hao Van, Xintao Wu

How to properly set the privacy parameter in differential privacy (DP) has been an open question in DP research since it was first proposed in 2006. In this work, we demonstrate the ability of influence functions to offer insight into how a specific privacy parameter value will affect a model's test loss in the randomized response-based local DP setting. Our proposed method allows a data curator to select the privacy parameter best aligned with their allowed privacy-utility trade-off without requiring heavy computation such as extensive model retraining and data privatization. We consider multiple common randomization scenarios, such as performing randomized response over the features, and/or over the labels, as well as the more complex case of applying a class-dependent label noise correction method to offset the noise incurred by randomization. Further, we provide a detailed discussion over the computational complexity of our proposed approach inclusive of an empirical analysis. Through empirical evaluations we show that for both binary and multi-class settings, influence functions are able to approximate the true change in test loss that occurs when randomized response is applied over features and/or labels with small mean absolute error, especially in cases where noise correction methods are applied.

📄 PDF Abstract BibTeX arXiv:2309.08678

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Evaluating Differentially Private Machine Learning in Practice

2019-02-24 · Bargav Jayaraman, David Evans

Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, $\epsilon$, about how much information is leaked by a mechanism. However, implementations of …

BIG-bench Machine LearningPrivacy Preserving

(Local) Differential Privacy has NO Disparate Impact on Fairness

2023-04-25 · Héber H. Arcolezi, Karima Makhlouf, Catuscia Palamidessi

In recent years, Local Differential Privacy (LDP), a robust privacy-preserving methodology, has gained widespread adoption in real-world applications. With LDP, users can perturb their data on their devices before sendin…

AttributeFairnessPrivacy Preserving

Removing Disparate Impact of Differentially Private Stochastic Gradient Descent on Model Accuracy

2020-03-08 · Depeng Xu, Wei Du, Xintao Wu

When we enforce differential privacy in machine learning, the utility-privacy trade-off is different w.r.t. each group. Gradient clipping and random noise addition disproportionately affect underrepresented and complex c…

Locally Differentially Private Online Federated Learning With Correlated Noise

2024-11-27 · Jiaojiao Zhang, Linglingzhi Zhu, Dominik Fay, Mikael Johansson

We introduce a locally differentially private (LDP) algorithm for online federated learning that employs temporally correlated noise to improve utility while preserving privacy. To address challenges posed by the correla…

Federated Learning

Profile-Based Privacy for Locally Private Computations

2019-01-21 · Joseph Geumlek, Kamalika Chaudhuri

Differential privacy has emerged as a gold standard in privacy-preserving data analysis. A popular variant is local differential privacy, where the data holder is the trusted curator. A major barrier, however, towards a …

Privacy Preserving