Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks
The wide adoption and application of Masked language models~(MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities -- to what extent do MLMs leak information about their training data? Prior attempts at measuring leakage of MLMs via membership inference attacks have been inconclusive, implying the potential robustness of MLMs to privacy attacks. In this work, we posit that prior attempts were inconclusive because they based their attack solely on the MLM's model score. We devise a stronger membership inference attack based on likelihood ratio hypothesis testing that involves an additional reference MLM to more accurately quantify the privacy risks of memorization in MLMs. We show that masked language models are extremely susceptible to likelihood ratio membership inference attacks: Our empirical results, on models trained on medical notes, show that our attack improves the AUC of prior membership inference attacks from 0.66 to an alarmingly high 0.90 level, with a significant improvement in the low-error region: at 1% false positive rate, our attack is 51X more powerful than prior work.
Code (0)
등록된 구현이 없습니다.
Tasks
Inference AttackMembership Inference AttackMemorizationSimilar Papers 제목 키워드 기반
Membership Inference Attack Susceptibility of Clinical Language Models
Deep Neural Network (DNN) models have been shown to have high empirical privacy leakages. Clinical language models (CLMs) trained on clinical data have been used to improve performance in biomedical natural language proc…
Inference AttackMembership Inference AttackOn the Privacy Risks of Model Explanations
Privacy and transparency are two key foundations of trustworthy machine learning. Model explanations offer insights into a model's decisions on input data, whereas privacy is primarily concerned with protecting informati…
modelR.R.: Unveiling LLM Training Privacy through Recollection and Ranking
Large Language Models (LLMs) pose significant privacy risks, potentially leaking training data due to implicit memorization. Existing privacy attacks primarily focus on membership inference attacks (MIAs) or data extract…
MemorizationMembership and Memorization in LLM Knowledge Distillation
Recent advances in Knowledge Distillation (KD) aim to mitigate the high computational demands of Large Language Models (LLMs) by transferring knowledge from a large ''teacher'' to a smaller ''student'' model. However, st…
Knowledge DistillationEvaluating the Dynamics of Membership Privacy in Deep Learning
Membership inference attacks (MIAs) pose a critical threat to the privacy of training data in deep learning. Despite significant progress in attack methodologies, our understanding of when and how models encode membershi…