Skip to content
AI News HubLIVE
Original source2 min read

Secure-by-Disguise: A Systematic Evaluation of Image Disguising for Confidential Medical Image Modeling

Summary

A new arXiv paper systematically evaluates image disguising techniques (DisguisedNets and NeuraCrypt) for privacy-preserving medical image classification and segmentation. The study finds that while these methods preserve utility for classification, they cause substantial degradation in dense semantic segmentation. Randomized Multidimensional Transformation (RMT) offers the best balance of performance and security, whereas AES-based disguising severely impacts utility. Reconstruction attacks effective on natural images are less successful on realistic medical images.

SourcearXiv Computer VisionAuthor: Jason Rojas, Jiajie He, Yash Patel, Yuechun Gu, Zeyun Yu, Keke Chen
Secure-by-Disguise: A Systematic Evaluation of Image Disguising for Confidential Medical Image Modeling
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 9 Jul 2026]

Title:Secure-by-Disguise: A Systematic Evaluation of Image Disguising for Confidential Medical Image Modeling

View a PDF of the paper titled Secure-by-Disguise: A Systematic Evaluation of Image Disguising for Confidential Medical Image Modeling, by Jason Rojas and 5 other authors

View PDF

Abstract:Cloud-based deep learning enables large-scale medical image analysis but raises significant privacy concerns when sensitive patient images are outsourced for model development. Image disguising has recently emerged as a promising privacy-enhancing technology (PET) that transforms images into visually unintelligible representations while preserving information for downstream learning. We established a unified framework to evaluate representative methods, DisguisedNets and NeuraCrypt, across four datasets involving classification and semantic segmentation tasks. Our analysis assessed predictive utility, efficiency, and robustness against reconstruction attacks. Results showed that image disguising performance varies significantly between tasks; while methods preserved utility for medical image classification, they caused substantial degradation in dense semantic segmentation. Specifically, Randomized Multidimensional Transformation (RMT) offered the optimal balance of performance and security, whereas AES-based disguising severely impacted utility. Furthermore, regression-based reconstruction attacks effective on natural images proved considerably less successful on realistic medical images. These findings provide a systematic assessment of PET suitability for confidential medical AI applications.

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Cite as: arXiv:2607.08867 [cs.CV]

(or arXiv:2607.08867v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2607.08867

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jason Rojas [view email] [v1] Thu, 9 Jul 2026 18:43:58 UTC (3,173 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Secure-by-Disguise: A Systematic Evaluation of Image Disguising for Confidential Medical Image Modeling, by Jason Rojas and 5 other authors

View PDF

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-07

Change to browse by:

cs cs.LG

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Image disguising preserves classification utility but significantly degrades semantic segmentation performance.
  • RMT provides the optimal balance between privacy and utility; AES-based methods severely harm model performance.
  • Reconstruction attacks designed for natural images are less effective on realistic medical images.

Highlights and analysis are generated automatically and may contain errors. Check the original source.