Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 449

The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

Open access
Zhang, Yuheng, Jia, Ruoxi, Pei, Hengzhi, Wang, Wenxiao, Li, Bo, Song, Dawn·2020·2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction by~\cite{fredrikson2014privacy}, such attacks have raised serious concerns given that training data usually contain privacy sensitive information. Thus far, successful model-inversion attacks have only been demonstrated on simple models, such as linear regression and logistic regression. Previous attempts to invert neural networks, even the ones with simple architectures, have failed to produce convincing results. Here we present a novel attack method, termed the \emph{generative model-inversion attack}, which can invert deep neural networks with high success rates. Rather than reconstructing private training data from scratch, we leverage partial public information, which can be very generic, to learn a distributional prior via generative adversarial networks (GANs) and use it to guide the inversion process. Moreover, we theoretically prove that a model's predictive power and its vulnerability to inversion attacks are indeed two sides of the same coin---highly predictive models are able to establish a strong correlation between features and labels, which coincides exactly with what an adversary exploits to mount the attacks. Our extensive experiments demonstrate that the proposed attack improves identification accuracy over the existing work by about $75\%$ for reconstructing face images from a state-of-the-art face recognition classifier. We also show that differential privacy, in its canonical form, is of little avail to defend against our attacks.

Overview

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1109/cvpr42600.2020.00033

Cites

26 of 26 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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 26 references

Research works printed but not linked: 2

  1. nguyen, 2016, Synthesizing the preferred inputs for neurons in neural networks via deep generator networks, Advances in neural information processing systems, 3387
  2. arjovsky, 2017, Wasserstein GAN

Cited by

See all 449

Metadata

Authors
Zhang, Y., Jia, R., Pei, H., Wang, W., Li, B., & Song, D.
Venue
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2020-06
Pages
250-258
ISSN
1063-6919 (ISSN-L)
OpenAlex
W3035616549
Cited by
449
References
26
FWCI
21.57
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: The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks. https://app.cochat.ai/papers/10.1109/cvpr42600.2020.00033
The paper
Zhang, Y., Jia, R., Pei, H., Wang, W., Li, B., & Song, D. (2020). The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr42600.2020.00033

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.