CoChat

When the Curious Abandon Honesty: Federated Learning Is Not Private

Open access
Boenisch, Franziska, Dziedzic, Adam, Schuster, Roei, Shamsabadi, Ali Shahin, Shumailov, Ilia, Papernot, Nicolas · 2023 · 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P)
Cited by 145

The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.

Abstract

In federated learning (FL), data does not leave personal devices when they are jointly training a machine learning model. Instead, these devices share gradients, parameters, or other model updates, with a central party (e.g., a company) coordinating the training. Because data never "leaves" personal devices, FL is often presented as privacy-preserving. Yet, recently it was shown that this protection is but a thin facade, as even a passive, honest-but-curious attacker observing gradients can reconstruct data of individual users contributing to the protocol.In this work, we show a novel data reconstruction attack which allows an active and dishonest central party to efficiently extract user data from the received gradients. While prior work on data reconstruction in FL relies on solving computationally expensive optimization problems or on making easily detectable modifications to the shared model’s architecture or parameters, in our attack the central party makes inconspicuous changes to the shared model’s weights before sending them out to the users. We call the modified weights of our attack trap weights.Our active attacker is able to recover user data perfectly, i.e., with zero error, even when this data stems from the same class. Recovery comes with near-zero costs: the attack requires no complex optimization objectives. Instead, our attacker exploits inherent data leakage from model gradients and simply amplifies this effect by maliciously altering the weights of the shared model through the trap weights. These specificities enable our attack to scale to fully-connected and convolutional deep neural networks trained with large mini-batches of data. For example, for the high-dimensional vision dataset ImageNet, we perfectly reconstruct more than 50% of the training data points from mini-batches as large as 100 data points. In textual tasks, such as IMDB sentiment analysis, more than 65% of data points from mini-batches containing 100 data points can be perfectly reconstructed.

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/eurosp57164.2023.00020

Cites

17 of 17 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

Show all 17 references

Cited by

See all 145

Metadata

Authors
Boenisch, F., Dziedzic, A., Schuster, R., Shamsabadi, A. S., Shumailov, I., & Papernot, N.
Venue
2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P)
Publisher
IEEE
Published
2023-07
Pages
175-199
OpenAlex
W4385412495
Cited by
145
References
17
FWCI
26.46
Type
conference paper
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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: When the Curious Abandon Honesty: Federated Learning Is Not Private. https://app.cochat.ai/papers/10.1109/eurosp57164.2023.00020
The paper
Boenisch, F., Dziedzic, A., Schuster, R., Shamsabadi, A. S., Shumailov, I., & Papernot, N. (2023). When the Curious Abandon Honesty: Federated Learning Is Not Private. 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P). https://doi.org/10.1109/eurosp57164.2023.00020

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.