paper-with-me

Papers

Nearly Tight Black-Box Auditing of Differentially Private Machine Learning

2024-05-23 · Meenatchi Sundaram Muthu Selva Annamalai, Emiliano De Cristofaro

This paper presents an auditing procedure for the Differentially Private Stochastic Gradient Descent (DP-SGD) algorithm in the black-box threat model that is substantially tighter than prior work. The main intuition is to craft worst-case initial model parameters, as DP-SGD's privacy analysis is agnostic to the choice of the initial model parameters. For models trained on MNIST and CIFAR-10 at theoretical $\varepsilon=10.0$, our auditing procedure yields empirical estimates of $\varepsilon_{emp} = 7.21$ and $6.95$, respectively, on a 1,000-record sample and $\varepsilon_{emp}= 6.48$ and $4.96$ on the full datasets. By contrast, previous audits were only (relatively) tight in stronger white-box models, where the adversary can access the model's inner parameters and insert arbitrary gradients. Overall, our auditing procedure can offer valuable insight into how the privacy analysis of DP-SGD could be improved and detect bugs and DP violations in real-world implementations. The source code needed to reproduce our experiments is available at https://github.com/spalabucr/bb-audit-dpsgd.

📄 PDF Abstract BibTeX arXiv:2405.14106

Code (1)

spalabucr/bb-audit-dpsgd 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Tight Auditing of Differentially Private Machine Learning

2023-02-15 · Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle 외

Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mechanisms are tight: the empirical privacy …

Federated Learning

Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios

2024-12-02 · Sangyeon Yoon, Wonje Jeung, Albert No

Auditing Differentially Private Stochastic Gradient Descent (DP-SGD) in the final model setting is challenging and often results in empirical lower bounds that are significantly looser than theoretical privacy guarantees…

Tight Auditing of Differential Privacy in MST and AIM

2026-04-20 · Georgi Ganev, Meenatchi Sundaram Muthu Selva Annamalai, Bogdan Kulynych arxiv

State-of-the-art Differentially Private (DP) synthetic data generators such as MST and AIM are widely used, yet tightly auditing their privacy guarantees remains challenging. We introduce a Gaussian Differential Privacy …

Optimizing Canaries for Privacy Auditing with Metagradient Descent

2025-07-21 · Matteo Boglioni, Terrance Liu, Andrew Ilyas, Zhiwei Steven Wu arxiv

In this work we study black-box privacy auditing, where the goal is to lower bound the privacy parameter of a differentially private learning algorithm using only the algorithm's outputs (i.e., final trained model). For …

Image Classification

Privacy Auditing with One (1) Training Run

2023-05-15 · NeurIPS 2023 11

We propose a scheme for auditing differentially private machine learning systems with a single training run. This exploits the parallelism of being able to add or remove multiple training examples independently. We analy…