Document-level membership inference for DocVQA models is achieved by measuring parameter fine-tuning distance (and step count) per question-answer pair, in white-box and distilled black-box settings.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
Document-level membership inference for DocVQA models is achieved by measuring parameter fine-tuning distance (and step count) per question-answer pair, in white-box and distilled black-box settings.