Metraipolis › archive › dc_44da1bf2b7ef

The Pen is Mightier than the Pixel: Natural Textual Unlearnable Example for Large Vision Language Models — arXiv:2611.04817

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.04817
License (as archived): CC0-1.0
Archived: 2026-11-04T18:34:48.061Z
SHA-256 of the archived text: b0b90e65f7d3bf923e93b01dfbc2d71260584dc28aa63c6e73273017f0171205
Stable URL of this page: https://metraipolis.com/documento/dc_44da1bf2b7ef

How to cite

The Pen is Mightier than the Pixel: Natural Textual Unlearnable Example for Large Vision Language Models — arXiv:2611.04817 — arXiv (en), https://arxiv.org/abs/2611.04817 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44da1bf2b7ef (Metraipolis archive dc_44da1bf2b7ef, sha256 b0b90e65f7d3bf923e93b01dfbc2d71260584dc28aa63c6e73273017f0171205)

BibTeX

@misc{dc44da1bf2b7ef,
  title = {The Pen is Mightier than the Pixel: Natural Textual Unlearnable Example for Large Vision Language Models — arXiv:2611.04817},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04817},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44da1bf2b7ef; sha256 b0b90e65f7d3bf923e93b01dfbc2d71260584dc28aa63c6e73273017f0171205},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04817. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The proliferation of Large Vision Language Models (LVLMs), trained on vast and often sensitive datasets, raised concerns regarding data privacy and unauthorized usage. Unlearnable Examples (UEs), which subtly perturb training data to mislead the models, have emerged as a promising defense method. This paper presents the first exploration of UEs specifically on LVLMs, which poses unique challenges due to their inherent multimodal nature. We propose a novel text-based perturbation method, Natural Textual Unlearnable Examples (NTUE), which can effectively mislead LVLMs by subtly manipulating the image label, establishing a shortcut between an identity of interest and a separate target, without introducing factual misinformation or affecting readability. Comprehensive experiments compared with traditional UE methods demonstrate the superior performance of NTUE. Our findings show that NTUE achieves a high success rate with a poison rate as low as 5%, underscoring its potential as a practical and robust solution for protecting multimodal data in the era of LVLMs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04817 — 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 2026-11-04T18:32:37.340Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).