Metraipolis › archive › dc_f98a64e8ffdf
FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators — arXiv:2609.30982
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30982
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T01:39:38.156Z
- SHA-256 of the archived text
5effcdbd15f471f39363b7ab6fbc829597e43916b579fccd77dc5ddcaafa21fd- Stable URL of this page
https://metraipolis.com/documento/dc_f98a64e8ffdf
How to cite
FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators — arXiv:2609.30982 — arXiv (en), https://arxiv.org/abs/2609.30982 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f98a64e8ffdf (Metraipolis archive dc_f98a64e8ffdf, sha256 5effcdbd15f471f39363b7ab6fbc829597e43916b579fccd77dc5ddcaafa21fd)
BibTeX
@misc{dcf98a64e8ffdf,
title = {FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators — arXiv:2609.30982},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30982},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f98a64e8ffdf; sha256 5effcdbd15f471f39363b7ab6fbc829597e43916b579fccd77dc5ddcaafa21fd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30982. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern AI image generators are increasingly deployed as opaque APIs, where customers can query the deployed service, but cannot inspect model weights or architecture. This creates a practical challenge: a provider may pass governance certification with one generator and later silently switch to a cheaper and lower-quality one for deployment, compromising public trust or even safety in high-stakes domains. We study integrity auditing at deployment time and propose FARE (Forensic Acceptance Region Estimation). A certified generator is enrolled by training FARE on images sampled from that generator. After deployment, FARE can determine whether a generated image is consistent with the enrolled generator---using only that image. FARE's features are based on image generator-specific artifacts that have been proposed for forensic applications. FARE amplifies these features during training by finding hard samples that tighten the acceptance region and increase sensitivity to subtle changes in the certified generator. Across generator swaps, including substitutions with similar model versions and model variants, FARE is effective at detecting swaps, consistently outperforming existing baselines at strict operating points, and remains effective under the exact-model and decision-only attacks evaluated in this work. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2609.30982 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T01:12:14.514Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).