Unintended Memorization of Sensitive Information in Fine-Tuned Language Models
Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII), which can violate privacy regulations and compromise individual safety. In this work, we systematically investigate a critical and underexplored vulnerability: the exposure of PII that appears only in model inputs, not in training targets. Using both synthetic and real-world datasets, we design controlled extraction probes to quantify unintended PII memorization and study how factors such as language, PII frequency, task type, and model size influence memorization behavior. We further benchmark four privacy-preserving approaches including differential privacy, machine unlearning, regularization, and preference alignment, evaluating their trade-offs between privacy and task performance. Our results show that post-training methods generally provide more consistent privacy-utility trade-offs, while differential privacy achieves strong reduction in leakage in specific settings, although it can introduce training instability. These findings highlight the persistent challenge of memorization in fine-tuned LLMs and emphasize the need for robust, scalable privacy-preserving techniques.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Understanding Unintended Memorization in Federated Learning
Recent works have shown that generative sequence models (e.g., language models) have a tendency to memorize rare or unique sequences in the training data. Since useful models are often trained on sensitive data, to ensur…
ClusteringFederated LearningMemorizationMitigating Unintended Memorization in Language Models via Alternating Teaching
Recent research has shown that language models have a tendency to memorize rare or unique sequences in the training corpora which can thus leak sensitive attributes of user data. We employ a teacher-student framework and…
MemorizationPrivacy PreservingUnderstanding Unintended Memorization in Language Models Under Federated Learning
Recent works have shown that language models (LMs), e.g., for next word prediction (NWP), have a tendency to memorize rare or unique sequences in the training data. Since useful LMs are often trained on sensitive data, i…
Federated LearningMemorizationScrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these mo…
Code GenerationExploring Memorization in Fine-tuned Language Models
Large language models (LLMs) have shown great capabilities in various tasks but also exhibited memorization of training data, raising tremendous privacy and copyright concerns. While prior works have studied memorization…
Memorization