[2607.25750] Detecting CSAM Text-to-Image LoRAs From Weights

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Machine Learning

arXiv:2607.25750 (cs)

[Submitted on 28 Jul 2026]

Title:Detecting CSAM Text-to-Image LoRAs From Weights

Authors:David Demitri Africa, Cate Heine, Nadine Staes-Polet, Kimberly Mai<br>View a PDF of the paper titled Detecting CSAM Text-to-Image LoRAs From Weights, by David Demitri Africa and 3 other authors

View PDF<br>HTML (experimental)

Abstract:Low-rank adaptation (LoRA) fine-tuning has made it cheap and easy to customize open-weight image generation models for specific tasks, including the production of child sexual abuse material (CSAM). Existing moderation relies on metadata or generated outputs, but metadata can be deceptive and generating outputs may itself be unacceptable or illegal. We show that a safer signal lives in the weights. The top-left singular vectors of a LoRA's updates form a compact, inference-free fingerprint ($u_1$) of its strongest learned change. Using human-subject age as a benign proxy for CSAM, we find that $u_1$ identifies what a LoRA was trained on, generalizes across base models, and abstains on unrelated benign content. The signal is robust to additive weight noise, rescaling, and precision reduction. These results indicate that harmful LoRAs could be screened directly from their weights without relying on metadata or generating harmful outputs.

Subjects:

Machine Learning (cs.LG); Computers and Society (cs.CY)

Cite as:<br>arXiv:2607.25750 [cs.LG]

(or<br>arXiv:2607.25750v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.25750

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Kimberly Mai [view email]<br>[v1]<br>Tue, 28 Jul 2026 14:12:52 UTC (4,553 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Detecting CSAM Text-to-Image LoRAs From Weights, by David Demitri Africa and 3 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.LG

next >

new<br>recent<br>| 2026-07

Change to browse by:

cs<br>cs.CY

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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?)

IArxiv recommender toggle

IArxiv Recommender<br>(What is IArxiv?)

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? |<br>Disable MathJax (What is MathJax?)

Major funding support from