Conference paper · 2022

When Deep Learning Meets Steganography: Protecting Inference Privacy in the Dark

Qin Liu, Jiamin Yang, Hongbo Jiang, Jie Wu, Tao Peng, Tian Wang, Guojun Wang

IEEE Conference on Computer Communications (INFOCOM), 590–599 · Published 2 May 2022 · DOI 10.1109/infocom48880.2022.9796975

View at the publisherCite this paper

In brief

“When Deep Learning Meets Steganography: Protecting Inference Privacy in the Dark” is a 2022 conference paper by Qin Liu and 6 co-authors, published in IEEE Conference on Computer Communications (INFOCOM). OpenAlex counts 16 citations as of 19 November 2026, which puts it in the top 8% of works published in 2022 by citations. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
16
Most cited in
2025 (4)
Field-weighted impact
0.81
References
58
Authors
7

Abstract

While cloud-based deep learning benefits for high-accuracy inference, it leads to potential privacy risks when exposing sensitive data to untrusted servers. In this paper, we work on exploring the feasibility of steganography in preserving inference privacy. Specifically, we devise GHOST and GHOST+, two private inference solutions employing steganography to make sensitive images invisible in the… Read the full abstract at the publisher.

Excerpt. This paper is not open access.

Cite this paper

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

APA 7

Liu, Q., Yang, J., Jiang, H., Wu, J., Peng, T., Wang, T., & Wang, G. (2022). When Deep Learning Meets Steganography: Protecting Inference Privacy in the Dark. IEEE Conference on Computer Communications (INFOCOM), 590–599. https://doi.org/10.1109/infocom48880.2022.9796975

MLA 9

Liu, Qin, et al. “When Deep Learning Meets Steganography: Protecting Inference Privacy in the Dark.” IEEE Conference on Computer Communications (INFOCOM), 2022, pp. 590–599. https://doi.org/10.1109/infocom48880.2022.9796975.

Chicago

Liu, Qin, Jiamin Yang, Hongbo Jiang, Jie Wu, Tao Peng, Tian Wang, and Guojun Wang. 2022. “When Deep Learning Meets Steganography: Protecting Inference Privacy in the Dark.” IEEE Conference on Computer Communications (INFOCOM): 590–599. https://doi.org/10.1109/infocom48880.2022.9796975.

Harvard

Liu, Q. et al. (2022) ‘When Deep Learning Meets Steganography: Protecting Inference Privacy in the Dark’, IEEE Conference on Computer Communications (INFOCOM), pp. 590–599. doi:10.1109/infocom48880.2022.9796975.

IEEE

Q. Liu et al., “When Deep Learning Meets Steganography: Protecting Inference Privacy in the Dark,” IEEE Conference on Computer Communications (INFOCOM), pp. 590–599, 2022, doi: 10.1109/infocom48880.2022.9796975.

BibTeX

@inproceedings{liu2022when,
  title     = {{When Deep Learning Meets Steganography: Protecting Inference Privacy in the Dark}},
  author    = {Liu, Qin and Yang, Jiamin and Jiang, Hongbo and Wu, Jie and Peng, Tao and Wang, Tian and Wang, Guojun},
  booktitle = {IEEE Conference on Computer Communications (INFOCOM)},
  year      = {2022},
  pages     = {590--599},
  doi       = {10.1109/infocom48880.2022.9796975},
  url       = {https://doi.org/10.1109/infocom48880.2022.9796975}
}

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

Citations by year

YearCitationsShare of the best year
202233
202333
202422
202544
202644

Its field-weighted citation impact is 0.81: it has been cited 0.81 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

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

  • steganography
  • inference privacy
  • private inference
  • cloud-based deep learning
  • adversarial attacks
  • adversarial perturbations
  • generative adversarial networks
  • data poisoning

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?

Liu, Q., Yang, J., Jiang, H., Wu, J., Peng, T., Wang, T., & Wang, G. (2022). When Deep Learning Meets Steganography: Protecting Inference Privacy in the Dark. IEEE Conference on Computer Communications (INFOCOM), 590–599. https://doi.org/10.1109/infocom48880.2022.9796975

How many times has this paper been cited?

16 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Qin Liu, Jiamin Yang, Hongbo Jiang, Jie Wu, Tao Peng, Tian Wang, Guojun Wang.

What is the DOI of this paper?

10.1109/infocom48880.2022.9796975, permanently at https://doi.org/10.1109/infocom48880.2022.9796975. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 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.