Metraipolis › archive › dc_53ffa1dedf60
PROVE: Training-Free Prompt Recovery using Verifiable Evidence — arXiv:2608.13671
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13671
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:02:10.952Z
- SHA-256 of the archived text
09df3902f22ff4d747ac32cfcea93bab3ffa06b2e794d08b0bc70b6b68b40fa2- Stable URL of this page
https://metraipolis.com/documento/dc_53ffa1dedf60
How to cite
PROVE: Training-Free Prompt Recovery using Verifiable Evidence — arXiv:2608.13671 — arXiv (en), https://arxiv.org/abs/2608.13671 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_53ffa1dedf60 (Metraipolis archive dc_53ffa1dedf60, sha256 09df3902f22ff4d747ac32cfcea93bab3ffa06b2e794d08b0bc70b6b68b40fa2)
BibTeX
@misc{dc53ffa1dedf60,
title = {PROVE: Training-Free Prompt Recovery using Verifiable Evidence — arXiv:2608.13671},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13671},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_53ffa1dedf60; sha256 09df3902f22ff4d747ac32cfcea93bab3ffa06b2e794d08b0bc70b6b68b40fa2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13671. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern text-to-image models can generate highly realistic images from natural-language prompts, while recent advances in prompt inversion have made it increasingly feasible to recover those prompts from generated outputs, raising new concerns for copyright protection and content ownership. As prompt marketplaces emerge, recovered prompts can enable both the unauthorized reproduction and redistribution of copyrighted creative works, and the exposure of the prompts that encode an artist's creative recipe in AI-generated content. Existing prompt inversion methods rely on gradient-based optimization, autoregressive captioning, or reinforcement learning. However, optimization-based methods often produce unreadable prompts, captioning methods hallucinate unverified details, and RL-based approaches frequently overfit to specific generators while introducing evaluation circularity. We introduce PROVE (Prompt Recovery with Verified Evidence), a training-free, black-box prompt inversion attack that reconstructs prompts by composing verifiable scene descriptions rather than optimizing token sequences, targeting both original copyrighted works and AI-generated content. The resulting prompts are fully auditable, with every recovered claim grounded in explicit image evidence, and are formalized through a precision-constrained recall maximization objective. Across MS-COCO, Flickr30K, and Lexica, using state-of-the-art text-to-image generators, PROVE consistently outperforms optimization, captioning, and RL-based baselines on image similarity (DINO, LPIPS) and text-image alignment (CLIP), without any training, generator access, or fine-tuning, demonstrating a stronger and more practical prompt inversion attack. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.13671 — 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 2026-10-19T03:57:57.752Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).