mlsanityData to 7 Oct 2026

On Reconstructing Training Data From Bayesian Posteriors and Trained Models

arXiv 2507.18372 ↗First posted 24 Jul 2025stat.ML cs.LG math.STcited by 0

Not on the map. Why?

Abstract (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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 34 references that are in the map. First posted on arXiv 24 Jul 2025.

Builds on

18 of 34 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  4. 2019Deep Leakage from Gradientscited by 1,004
  5. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  6. 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 360
  7. 2022Reconstructing Training Data with Informed Adversariescited by 143
  8. 2022Reconstructing Training Data from Trained Neural Networkscited by 129
  9. 2023Data Distillation: A Surveycited by 86
  10. 2022Bounding Training Data Reconstruction in Private (Deep) Learningcited by 43
  11. 2023Bounding Training Data Reconstruction in DP-SGDcited by 42
  12. 2020Differentially Private Simple Linear Regressioncited by 33
6 more
  1. 2019Differentially Private Bayesian Linear Regressioncited by 24
  2. 2023Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Lossescited by 24
  3. 2023Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillationcited by 14
  4. 2023Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacycited by 14
  5. 2023Machine Learning and the Future of Bayesian Computationcited by 4
  6. 2023Bayes Hilbert Spaces for Posterior Approximationcited by 1

Built on by

Not cited yet.