A temperature-perturbed black-box attack infers video training membership in VideoLLMs with 0.68 AUC by exploiting sharper generation behavior on member samples.
arXiv preprint arXiv:2602.10639 (2026)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Membership Inference Attacks Against Video Large Language Models
A temperature-perturbed black-box attack infers video training membership in VideoLLMs with 0.68 AUC by exploiting sharper generation behavior on member samples.