paper-with-me

홈 › Papers

On Reconstructing Training Data From Bayesian Posteriors and Trained Models

2025-07-24 · George Wynne arxiv

Publicly releasing the specification of a model with its trained parameters means an adversary can attempt to reconstruct information about the training data via training data reconstruction attacks, a major vulnerability of modern machine learning methods. This paper makes three primary contributions: establishing a mathematical framework to express the problem, characterising the features of the training data that are vulnerable via a maximum mean discrepancy equivalance and outlining a score matching framework for reconstructing data in both Bayesian and non-Bayesian models, the former is a first in the literature.

📄 PDF Abstract BibTeX arXiv:2507.18372

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A variational neural Bayes framework for inference on intractable posterior distributions

2024-04-16 · Elliot Maceda, Emily C. Hector, Amanda Lenzi, Brian J. Reich

Classic Bayesian methods with complex models are frequently infeasible due to an intractable likelihood. Simulation-based inference methods, such as Approximate Bayesian Computing (ABC), calculate posteriors without acce…

Uncertainty Quantification

Bayesian Joint Chance Constrained Optimization: Approximations and Statistical Consistency

2021-06-23 · Prateek Jaiswal, Harsha Honnappa, Vinayak A. Rao

This paper considers data-driven chance-constrained stochastic optimization problems in a Bayesian framework. Bayesian posteriors afford a principled mechanism to incorporate data and prior knowledge into stochastic opti…

Stochastic Optimization

Practical calibration of the temperature parameter in Gibbs posteriors

2020-04-22 · Lucie Perrotta

PAC-Bayesian algorithms and Gibbs posteriors are gaining popularity due to their robustness against model misspecification even when Bayesian inference is inconsistent. The PAC-Bayesian alpha-posterior is a generalizatio…

Bayesian Inference

Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning

2019-05-17 · Mike Walmsley, Lewis Smith, Chris Lintott, Yarin Gal 외

We use Bayesian convolutional neural networks and a novel generative model of Galaxy Zoo volunteer responses to infer posteriors for the visual morphology of galaxies. Bayesian CNN can learn from galaxy images with uncer…

Active Learning

Scalable Bayesian Learning with posteriors

2024-05-31 · Samuel Duffield, Kaelan Donatella, Johnathan Chiu, Phoebe Klett 외

Although theoretically compelling, Bayesian learning with modern machine learning models is computationally challenging since it requires approximating a high dimensional posterior distribution. In this work, we (i) intr…