Metraipolis › archive › dc_5bb9f303e83e

Beyond Visual Evidence: Revealing and Mitigating Relational Privacy Leakage in Document MLLMs — arXiv:2608.12911

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12911
License (as archived)
CC0-1.0
Archived
2026-10-19T04:26:19.727Z
SHA-256 of the archived text
4ff12ec0ea90482a94001c8e51ed86d4dcf36d5d0333b378f9431810d3339db0
Stable URL of this page
https://metraipolis.com/documento/dc_5bb9f303e83e

How to cite

Beyond Visual Evidence: Revealing and Mitigating Relational Privacy Leakage in Document MLLMs — arXiv:2608.12911 — arXiv (en), https://arxiv.org/abs/2608.12911 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5bb9f303e83e (Metraipolis archive dc_5bb9f303e83e, sha256 4ff12ec0ea90482a94001c8e51ed86d4dcf36d5d0333b378f9431810d3339db0)
BibTeX
@misc{dc5bb9f303e83e,
  title = {Beyond Visual Evidence: Revealing and Mitigating Relational Privacy Leakage in Document MLLMs — arXiv:2608.12911},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12911},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5bb9f303e83e; sha256 4ff12ec0ea90482a94001c8e51ed86d4dcf36d5d0333b378f9431810d3339db0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12911. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While the privacy risks of multimodal large language models (MLLMs) have drawn significant attention, the unique vulnerabilities of domain-specific MLLMs remain largely underexplored. Focusing on document understanding MLLMs for identity document processing, this paper investigates the privacy issues inherent in Key Information Extraction (KIE) tasks. We reveal that when input images lack sufficient visual evidence, these models often rely on memorized field relations from training data to infer missing content, thereby leaking multiple correlated fields containing sensitive personal information. To mitigate this risk, we make three key this http URL , we propose the Dynamic Relational Unlearning Framework (DRUF) which comprises a Relational Decoupling Unlearning (RDU) module and a dynamic set update mechanism. It suppresses the leakage of high-risk field pairs while preserving KIE this http URL , we introduce DocPrivacyBench, a novel benchmark to systematically evaluate a model's susceptibility to privacy leakage under conditions of absent or minimal visual this http URL , we evaluate three MLLMs and six unlearning methods using this benchmark, assessing both post-unlearning leakage suppression and utility this http URL results demonstrate that existing MLLMs consistently exhibit privacy leakage when visual evidence is scarce, particularly on noisier datasets. In contrast, DRUF outperforms the strongest baseline by improving leakage suppression by 4.8 percentage points, effectively mitigating privacy risks while maintaining robust document information extraction performance.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CR).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Cryptography and Security (cs.CR); Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.12911 — 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 2026-10-19T04:20:00.577Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).