Metraipolis › archive › dc_cafa67aafdeb

MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoning — arXiv:2608.17722

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.17722
License (as archived): CC0-1.0
Archived: 2026-10-18T14:49:06.843Z
SHA-256 of the archived text: 79d92cc87dc3a663c5cde96bbd6b2580ddd2cfa3d57f265c1c4f06dc8e5291f1
Stable URL of this page: https://metraipolis.com/documento/dc_cafa67aafdeb

How to cite

MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoning — arXiv:2608.17722 — arXiv (en), https://arxiv.org/abs/2608.17722 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cafa67aafdeb (Metraipolis archive dc_cafa67aafdeb, sha256 79d92cc87dc3a663c5cde96bbd6b2580ddd2cfa3d57f265c1c4f06dc8e5291f1)

BibTeX

@misc{dccafa67aafdeb,
  title = {MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoning — arXiv:2608.17722},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.17722},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cafa67aafdeb; sha256 79d92cc87dc3a663c5cde96bbd6b2580ddd2cfa3d57f265c1c4f06dc8e5291f1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17722. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language models (VLMs) achieve outstanding performance largely due to the amount of training data available on the internet. At the same time, data holders (e.g., artists) urgently need to determine whether their data has been used for model training without authorization, which concerns both intellectual property rights and personal privacy. Data auditing, particularly through membership inference (MI), has attracted attention as a direct tool. This work proposes MemCatalyst, a set of data poisoning tools, aiming to amplify the data auditing performance on VLMs. MemCatalyst employs two strategies: Poisoning Text (PT) and Poisoning Image (PI). MemCatalyst forces VLMs to over-learn specific inconsistencies between image features and textual semantics during training, thereby increasing their susceptibility to membership information auditing. Crucially, the transferability of poisoned samples across different VLM architectures is demonstrated to be effective in the black-box setting. Extensive evaluations using five state-of-the-art data audits on two prominent VLMs demonstrate that MemCatalyst markedly enhances MI AUC scores with a minimal budget of poisoned samples, while maintaining a negligible impact on model performance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.LG).
Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.17722 — 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 2026-10-18T14:47:59.468Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).