paper-with-me

Papers

Bounding Training Data Reconstruction in Private (Deep) Learning

2022-01-28 · Chuan Guo, Brian Karrer, Kamalika Chaudhuri, Laurens van der Maaten

Differential privacy is widely accepted as the de facto method for preventing data leakage in ML, and conventional wisdom suggests that it offers strong protection against privacy attacks. However, existing semantic guarantees for DP focus on membership inference, which may overestimate the adversary's capabilities and is not applicable when membership status itself is non-sensitive. In this paper, we derive the first semantic guarantees for DP mechanisms against training data reconstruction attacks under a formal threat model. We show that two distinct privacy accounting methods -- Renyi differential privacy and Fisher information leakage -- both offer strong semantic protection against data reconstruction attacks.

📄 PDF Abstract BibTeX arXiv:2201.12383

Code (1)

facebookresearch/bounding_data_reconstruction 공식 구현 jax

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

Bounding Training Data Reconstruction in DP-SGD

2023-02-14 · NeurIPS 2023 11

Differentially private training offers a protection which is usually interpreted as a guarantee against membership inference attacks. By proxy, this guarantee extends to other threats like reconstruction attacks attempti…

Reconstruction Attack

Reconstruction Attack on Instance Encoding for Language Understanding

2021-11-01 · EMNLP 2021 11 · Shangyu Xie, Yuan Hong

A private learning scheme TextHide was recently proposed to protect the private text data during the training phase via so-called instance encoding. We propose a novel reconstruction attack to break TextHide by recoverin…

Privacy PreservingReconstruction AttackSentenceSentence Classification

Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data

2024-02-06 · Yvonne Zhou, Mingyu Liang, Ivan Brugere, Dana Dachman-Soled 외

The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset. To prevent leakage of sensitive data, we consi…

Smoothly Bounding User Contributions in Differential Privacy

2020-12-01 · NeurIPS 2020 12 · Alessandro Epasto, Mohammad Mahdian, Jieming Mao, Vahab Mirrokni 외

A differentially private algorithm guarantees that the input of a single user won’t significantly change the output distribution of the algorithm. When a user contributes more data points, more information can be collect…

DP-SNP-TIHMM: Differentially Private, Time-Inhomogeneous Hidden Markov Models for Synthesizing Genome-Wide Association Datasets

2025-10-07 · Shadi Rahimian, Mario Fritz arxiv

Single nucleotide polymorphism (SNP) datasets are fundamental to genetic studies but pose significant privacy risks when shared. The correlation of SNPs with each other makes strong adversarial attacks such as masked-val…