Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.00788 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917453358956544 |
|---|---|
| author | Arthur, Adam Schwartz, Christopher |
| author_facet | Arthur, Adam Schwartz, Christopher |
| contents | Public image diffusion models are now powerful enough that an attacker without the resources to train a tabular-specific generator may repurpose one off the shelf. This study tests that possibility directly. An unmodified Stable Diffusion U-Net is applied to the UCI Adult Income dataset by reshaping each row into a small single-channel pseudo-image. The architecture's inductive bias toward spatial locality makes feature placement a design variable, and several layouts are tested. However, this is only the beginning of the story, as this paper also draws two philosophical distinctions. One separates statistical from perceptual realism: whether synthetic content holds up to a machine's correlation audits or a human's sensory inspection. The other introduces synthetic evidence as a category alongside synthetic media: AI-generated material whose consumer is a machine in a closed evidentiary pipeline rather than a person in an open information system. An attacker succeeds with synthetic evidence by thinking like the machine that will receive it. And the more the attacker succeeds, the more they can induce ground truth drift: the silent reclassification of AI-generated outputs as authentic when reused in pipelines that do not interrogate their provenance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00788 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Repurposing Image Diffusion Models for Adversarial Synthetic Structured Data: A Case Study of Ground Truth Drift Arthur, Adam Schwartz, Christopher Cryptography and Security Public image diffusion models are now powerful enough that an attacker without the resources to train a tabular-specific generator may repurpose one off the shelf. This study tests that possibility directly. An unmodified Stable Diffusion U-Net is applied to the UCI Adult Income dataset by reshaping each row into a small single-channel pseudo-image. The architecture's inductive bias toward spatial locality makes feature placement a design variable, and several layouts are tested. However, this is only the beginning of the story, as this paper also draws two philosophical distinctions. One separates statistical from perceptual realism: whether synthetic content holds up to a machine's correlation audits or a human's sensory inspection. The other introduces synthetic evidence as a category alongside synthetic media: AI-generated material whose consumer is a machine in a closed evidentiary pipeline rather than a person in an open information system. An attacker succeeds with synthetic evidence by thinking like the machine that will receive it. And the more the attacker succeeds, the more they can induce ground truth drift: the silent reclassification of AI-generated outputs as authentic when reused in pipelines that do not interrogate their provenance. |
| title | Repurposing Image Diffusion Models for Adversarial Synthetic Structured Data: A Case Study of Ground Truth Drift |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2605.00788 |