Leverage Unlearning to Sanitize LLMs
Pre-trained large language models (LLMs) are becoming useful for various tasks. To improve their performance on certain tasks, it is necessary to fine-tune them on specific data corpora (e.g., medical reports, business data). These specialized data corpora may contain sensitive data (e.g., personal or confidential data) that will be memorized by the model and likely to be regurgitated during its subsequent use. This memorization of sensitive information by the model poses a significant privacy or confidentiality issue. To remove this memorization and sanitize the model without requiring costly additional fine-tuning on a secured data corpus, we propose SANI. SANI is an unlearning approach to sanitize language models. It relies on both an erasure and repair phases that 1) reset certain neurons in the last layers of the model to disrupt the memorization of fine-grained information, and then 2) fine-tune the model while avoiding memorizing sensitive information. We comprehensively evaluate SANI to sanitize both a model fine-tuned and specialized with medical data by removing directly and indirectly identifiers from the memorization of the model, and a standard pre-trained model by removing specific terms defined as confidential information from the model. Results show that with only few additional epochs of unlearning, the model is sanitized and the number of regurgitations is drastically reduced. This approach can be particularly useful for hospitals or other industries that have already spent significant resources training models on large datasets and wish to sanitize them before sharing.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
Long context LLMs are vulnerable to prompt injection, where an attacker can inject an instruction in a long context to induce an LLM to generate an attacker-desired output. Existing prompt injection defenses are designed…
SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector
Large Language Model (LLM) unlearning aims to remove undesirable knowledge or behaviors while preserving retained capabilities. Current unlearning methods all involve a trade-off between unlearning and retention. We have…
Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
Large language models (LLMs) have shown to pose social and ethical risks such as generating toxic language or facilitating malicious use of hazardous knowledge. Machine unlearning is a promising approach to improve LLM s…
AttributeMachine UnlearningVisual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning
Unlearning in Multimodal Large Language Models (MLLMs) prevents the model from revealing private information when queried about target images. Existing MLLM unlearning methods largely adopt approaches developed for LLMs.…
Question AnsweringUnlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs
Unlearning in large language models (LLMs) involves precisely removing specific information from a pre-trained model. This is crucial to ensure safety of LLMs by deleting private data or harmful knowledge acquired during…