Skip to content
AI News HubLIVE
Original source2 min read

Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation

Summary

A study accepted at EMNLP 2026 main conference shows that vision-language models often comply with requests to transform faces into specific racial or sexual orientation identities, producing statistically distinguishable images that amplify stereotypes and propagate bias into textual reasoning and criminality profiling.

SourcearXiv Computer VisionAuthor: Soumyajit Datta, Arka Dutta, Ashiqur R. KhudaBukhsh
Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation
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 6 Oct 2026]

Title:Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation

View a PDF of the paper titled Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation, by Soumyajit Datta and Arka Dutta and Ashiqur R. KhudaBukhsh

View PDF HTML (experimental)

Abstract:Emergent generative AI technologies, while remarkably beneficial across several tasks and domains, can suffer from unforeseen vulnerabilities and difficult-to-anticipate failure modes. Such failure modes can disparately affect vulnerable communities. This paper investigates two well-known vision language models (VLMs) and inspects how these models encode protected identities while generating images. We show that when VLMs are requested to transform human face images to reflect race identities (e.g., Hispanic, Black, White, or Asian) and sexual orientation (e.g., gay or straight), VLMs often comply with such requests. We demonstrate that compliance (and refusal) is non-deterministic, group-sensitive, and generated images are statistically distinguishable, often accentuating deep-seated stereotypes. We further show that representation biases introduced during image generation can re-emerge in textual reasoning and characterization tasks. Finally, we show that this worrisome finding is not limited to racial identity or sexual orientation, image generation can perpetuate bias around criminality, raising concerning possibilities of AI-assisted profiling.

Comments: Accepted at EMNLP 2026 (Main Conference Track)

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY)

Cite as: arXiv:2610.35910 [cs.CV]

(or arXiv:2610.35910v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2610.35910

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Ashiqur Rahman KhudaBukhsh [view email] [v1] Tue, 6 Oct 2026 17:00:47 UTC (44,868 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation, by Soumyajit Datta and Arka Dutta and Ashiqur R. KhudaBukhsh

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-10

Change to browse by:

cs cs.AI cs.CL cs.CY

References & Citations

SciX

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

EngineersAdvanced

Key points

  • Vision-language models frequently comply with requests to transform human faces to reflect race identities or sexual orientation, with compliance being non-deterministic and group-sensitive.
  • Generated images are statistically distinguishable and often accentuate deep-seated stereotypes.
  • Representation biases introduced during image generation re-emerge in textual reasoning and characterization tasks.
  • The issue extends beyond race and sexual orientation, with image generation perpetuating bias around criminality and raising concerns about AI-assisted profiling.

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

More recent stories on this topic · Models