betaFeedback

WorksComputer Science

SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing

Abstract

Auditing whether a text-to-image (T2I) model was fine-tuned on a particular image collection is difficult: a model can absorb collection-level visual characteristics without reproducing training images. Proactive dataset-use auditing plants a shared signal in a dataset before release, then later checks whether that signal appears in a suspect model's generated outputs. Existing approaches often trade off verifiability, fidelity, robustness, and deployability. We introduce SpectralCanary\textbf{SpectralCanary}, which uses a smooth low-pass mask to blend a fixed canary image into every collection image while leaving captions unchanged and requiring neither auxiliary generation nor per-image optimization. A lightweight verifier detects the transferred signal in suspect-model outputs. Across eight tests on the Pokemon dataset and three realistic data transformations, spanning two architectures families, SpectralCanary achieves the highest average per-generation TPR@1%1\% FPR (91.1%91.1\%) and fixed threshold model-level accuracy using 30 generations (94.8%94.8\%) among the evaluated methods. Across five datasets spanning artistic, medical, satellite, and fashion domains with SD3.5, SpectralCanary averages 92.4%92.4\% per-generation TPR@1%1\% FPR while preserving the released images (SSIM 0.9890.989, LPIPS 0.0220.022) with a near-zero mean change FID (mean ΔΔFID 0.050.05) across datasets. Matched-energy ablations on Pokemon and ROCOv2 support our design choice, low-frequency placement transfers more reliably compared to mid/high-frequency placement. Under the evaluated adaptive attacks, the most effective removal requires aggressive modification and incurs more than 2525 ΔΔFID points. These results identify low-frequency visual signals as effective carriers for collection-level T2I audit traces.

Paper details

vlnc:W_uv3x9257
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
arXiv nonexclusive license
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Computer Science

Not recorded for this paper

View statement
Looking for related papers…