Presents SimA, a score-based single-query membership inference attack for diffusion models and LDMs that uses denoiser output norm to reveal training set proximity and outperforms multi-query baselines on eight datasets.
Membership inference attacks against machine learning models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Min-K% Prob detects pretraining data in LLMs by flagging outlier low-probability words in text, achieving 7.4% better performance than prior methods on the new WIKIMIA benchmark.
TOFU is a new benchmark with synthetic profiles and metrics demonstrating that existing unlearning algorithms for LLMs fail to achieve effective forgetting of targeted information.
citing papers explorer
-
Score-based Membership Inference on Diffusion Models
Presents SimA, a score-based single-query membership inference attack for diffusion models and LDMs that uses denoiser output norm to reveal training set proximity and outperforms multi-query baselines on eight datasets.
-
Detecting Pretraining Data from Large Language Models
Min-K% Prob detects pretraining data in LLMs by flagging outlier low-probability words in text, achieving 7.4% better performance than prior methods on the new WIKIMIA benchmark.
-
TOFU: A Task of Fictitious Unlearning for LLMs
TOFU is a new benchmark with synthetic profiles and metrics demonstrating that existing unlearning algorithms for LLMs fail to achieve effective forgetting of targeted information.