VeilProbe claims automatic black-box detection of LLM pre-training text, but its reported gains likely stem from a transductive evaluation where the feature extractor is trained on the test texts.
Do membership inference attacks work on large language models?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Automated Detection of Pre-training Text in Black-box LLMs
VeilProbe claims automatic black-box detection of LLM pre-training text, but its reported gains likely stem from a transductive evaluation where the feature extractor is trained on the test texts.