MCMC for Bayesian estimation of Differential Privacy from Membership Inference Attacks
We propose a new framework for Bayesian estimation of differential privacy, incorporating evidence from multiple membership inference attacks (MIA). Bayesian estimation is carried out via a Markov chain Monte Carlo (MCMC) algorithm, named MCMC-DP-Est, which provides an estimate of the full posterior distribution of the privacy parameter (e.g., instead of just credible intervals). Critically, the proposed method does not assume that privacy auditing is performed with the most powerful attack on the worst-case (dataset, challenge point) pair, which is typically unrealistic. Instead, MCMC-DP-Est jointly estimates the strengths of MIAs used and the privacy of the training algorithm, yielding a more cautious privacy analysis. We also present an economical way to generate measurements for the performance of an MIA that is to be used by the MCMC method to estimate privacy. We present the use of the methods with numerical examples with both artificial and real data.
Code (1)
Similar Papers 제목 키워드 기반
Statistic Selection and MCMC for Differentially Private Bayesian Estimation
This paper concerns differentially private Bayesian estimation of the parameters of a population distribution, when a statistic of a sample from that population is shared in noise to provide differential privacy. This wo…
Bayesian InferenceOn Connecting Stochastic Gradient MCMC and Differential Privacy
Significant success has been realized recently on applying machine learning to real-world applications. There have also been corresponding concerns on the privacy of training data, which relates to data security and conf…
BIG-bench Machine LearningBayesian Estimation of Differential Privacy
Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and th…
Differentially Private Distributed Bayesian Linear Regression with MCMC
We propose a novel Bayesian inference framework for distributed differentially private linear regression. We consider a distributed setting where multiple parties hold parts of the data and share certain summary statisti…
Bayesian InferencePrivacy PreservingregressionDP-Fast MH: Private, Fast, and Accurate Metropolis-Hastings for Large-Scale Bayesian Inference
Bayesian inference provides a principled framework for learning from complex data and reasoning under uncertainty. It has been widely applied in machine learning tasks such as medical diagnosis, drug design, and policyma…
Bayesian InferenceDrug DesignMedical DiagnosisPrivacy Preserving