3 papers
cs.LG2025
(Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMs
Jiashu Tao, Reza Shokri
Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now t…
cs.LG2025
Machine Learning from Explanations
Jiashu Tao, Reza Shokri
Acquiring and training on large-scale labeled data can be impractical due to cost constraints. Additionally, the use of small training datasets can result in considerable variabili…
cs.LG2025
Range Membership Inference Attacks
Jiashu Tao, Reza Shokri
Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), onl…