CoChat

Do Gradient Inversion Attacks Make Federated Learning Unsafe?

Open access
Hatamizadeh, Ali, Yin, Hongxu, Molchanov, Pavlo, Myronenko, Andriy, Li, Wenqi, Dogra, Prerna, Feng, Andrew, Flores, Mona G, Kautz, Jan, Xu, Daguang, Roth, Holger R. · 2023 · IEEE Transactions on Medical Imaging
Cited by 125

The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.

Abstract

Federated learning (FL) allows the collaborative training of AI models without needing to share raw data. This capability makes it especially interesting for healthcare applications where patient and data privacy is of utmost concern. However, recent works on the inversion of deep neural networks from model gradients raised concerns about the security of FL in preventing the leakage of training data. In this work, we show that these attacks presented in the literature are impractical in FL use-cases where the clients' training involves updating the Batch Normalization (BN) statistics and provide a new baseline attack that works for such scenarios. Furthermore, we present new ways to measure and visualize potential data leakage in FL. Our work is a step towards establishing reproducible methods of measuring data leakage in FL and could help determine the optimal tradeoffs between privacy-preserving techniques, such as differential privacy, and model accuracy based on quantifiable metrics.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tmi.2023.3239391

Cites

34 of 34 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Cited by

See all 125

Metadata

Authors
Hatamizadeh, A., Yin, H., Molchanov, P., Myronenko, A., Li, W., Dogra, P., Feng, A., Flores, M. G., Kautz, J., Xu, D., & Roth, H. R.
Venue
IEEE Transactions on Medical Imaging
Published
2023-07
Volume
42
Issue
7
Pages
2044-2056
ISSN
  • 0278-0062 (ISSN-L)
  • 1558-254X
OpenAlex
W4318242821
Cited by
125
References
34
FWCI
10.89
Type
journal article
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.