CheckMIABench converts LLMs with intermediate checkpoints into clean MIA testbeds by using pre- and post-checkpoint training data from the same distribution and evaluates published attacks on Pythia and OLMo models while releasing an open-source library.
arXiv preprint arXiv:2005.10881 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3representative citing papers
Empirical benchmarks show distribution similarity between adaptation and pretraining data increases practical privacy leakage in DP-adapted LLMs at fixed theoretical guarantees, with LoRA providing strongest protection for OOD cases.
Presents a systematic framework for evaluating MIAs across the full ML pipeline with standardized threat models and complementary metrics for different cost scenarios.
citing papers explorer
-
CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models
CheckMIABench converts LLMs with intermediate checkpoints into clean MIA testbeds by using pre- and post-checkpoint training data from the same distribution and evaluates published attacks on Pythia and OLMo models while releasing an open-source library.
-
Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
Empirical benchmarks show distribution similarity between adaptation and pretraining data increases practical privacy leakage in DP-adapted LLMs at fixed theoretical guarantees, with LoRA providing strongest protection for OOD cases.
-
A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning
Presents a systematic framework for evaluating MIAs across the full ML pipeline with standardized threat models and complementary metrics for different cost scenarios.