paperAugust 2026Unreviewed

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

Xukun Luan, Jinyan Liu, Yuhui Gong, Yuanguo Bi, Bing Hu, Xuesong Li, Di Wang

Abstract

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 da

Framework mappings

OWASP Top 10 for LLM Applications

LLM02Sensitive Information Disclosure
LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data
AML.T0024.000Infer Training Data Membership

Suggested from the entry's categories.

Cite

@misc{luan2026memcatalyst,
  title = {{MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoning}},
  author = {Xukun Luan and Jinyan Liu and Yuhui Gong and Yuanguo Bi and Bing Hu and Xuesong Li and Di Wang},
  year = {2026},
  month = aug,
  eprint = {2608.17722},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.17722}
}