Journal article · 2026 · Open access

Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization

Hao Fang, Wenbo Yu, Bin Chen, Xuan Wang, Shu‐Tao Xia, Qing Liao, Ke Xu

IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–16 · Published 9 November 2026 · DOI 10.1109/tpami.2026.3751908

Open PDFView at the publisherCite this paper

In brief

“Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization” is a 2026 journal article by Hao Fang and 6 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 3 citations as of 18 November 2026, which puts it in the top 4% of works published in 2026 by citations. It is open access under a CC BY-NC-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
3
Most cited in
2026 (3)
Field-weighted impact
3.24
References
43
Authors
7

Abstract

Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning, allowing multiple clients to collaboratively train a global model by transmitting locally computed gradients to a central server without exposing their private data. Nonetheless, recent studies find that the gradients exchanged in the FL system are also vulnerable to privacy leakage, e.g., an attacker can invert shared gradients to reconstruct sensitive data by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. However, existing attacks simply perform gradient inversion in the latent space of the GAN model, which limits their expression ability and generalizability. To tackle these challenges, we propose Gradient Inversion over Feature Domains (GIFD), which disassembles the GAN model and searches the hierarchical features of the intermediate layers. Instead of optimizing only over the initial latent code, we progressively change the optimized layer, from the initial latent space to intermediate layers closer to the output images. In addition, we design a regularizer to avoid unreal image generation by adding a small ${l_{1}}$ ball constraint to the searching range. We also extend GIFD to the out-of-distribution (OOD) setting, which weakens the assumption that the training sets of GANs and FL tasks obey the same data distribution. Furthermore, we consider the challenging OOD scenario of label inconsistency and propose a label mapping technique as an effective solution. Extensive experiments demonstrate that our method can achieve high-quality reconstruction and outperform competitive baselines across a variety of FL scenarios.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Fang, H., Yu, W., Chen, B., Wang, X., Xia, S., Liao, Q., & Xu, K. (2026). Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–16. https://doi.org/10.1109/tpami.2026.3751908

MLA 9

Fang, Hao, et al. “Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–16. https://doi.org/10.1109/tpami.2026.3751908.

Chicago

Fang, Hao, Wenbo Yu, Bin Chen, Xuan Wang, Shu‐Tao Xia, Qing Liao, and Ke Xu. 2026. “Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–16. https://doi.org/10.1109/tpami.2026.3751908.

Harvard

Fang, H. et al. (2026) ‘Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–16. doi:10.1109/tpami.2026.3751908.

IEEE

H. Fang et al., “Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–16, 2026, doi: 10.1109/tpami.2026.3751908.

BibTeX

@article{fang2026enhancing,
  title     = {{Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization}},
  author    = {Fang, Hao and Yu, Wenbo and Chen, Bin and Wang, Xuan and Xia, Shu‐Tao and Liao, Qing and Xu, Ke},
  journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year      = {2026},
  volume    = {PP},
  pages     = {1--16},
  doi       = {10.1109/tpami.2026.3751908},
  url       = {https://doi.org/10.1109/tpami.2026.3751908}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • gradient inversion attacks
  • federated learning privacy
  • generative adversarial networks
  • out-of-distribution generalization
  • label inconsistency
  • privacy leakage

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Fang, H., Yu, W., Chen, B., Wang, X., Xia, S., Liao, Q., & Xu, K. (2026). Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–16. https://doi.org/10.1109/tpami.2026.3751908

How many times has this paper been cited?

3 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Hao Fang, Wenbo Yu, Bin Chen, Xuan Wang, Shu‐Tao Xia, Qing Liao, Ke Xu.

What is the DOI of this paper?

10.1109/tpami.2026.3751908, permanently at https://doi.org/10.1109/tpami.2026.3751908. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.