On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models
The pretraining and fine-tuning approach has become the leading technique for various NLP applications. However, recent studies reveal that fine-tuning data, due to their sensitive nature, domain-specific characteristics, and identifiability, pose significant privacy concerns. To help develop more privacy-resilient fine-tuning models, we introduce a novel active privacy auditing framework, dubbed Parsing, designed to identify and quantify privacy leakage risks during the supervised fine-tuning (SFT) of language models (LMs). The framework leverages improved white-box membership inference attacks (MIAs) as the core technology, utilizing novel learning objectives and a two-stage pipeline to monitor the privacy of the LMs' fine-tuning process, maximizing the exposure of privacy risks. Additionally, we have improved the effectiveness of MIAs on large LMs including GPT-2, Llama2, and certain variants of them. Our research aims to provide the SFT community of LMs with a reliable, ready-to-use privacy auditing tool, and to offer valuable insights into safeguarding privacy during the fine-tuning process. Experimental results confirm the framework's efficiency across various models and tasks, emphasizing notable privacy concerns in the fine-tuning process. Project code available for https://anonymous.4open.science/r/PARSING-4817/.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Advancing the State-of-the-Art in Empirical Privacy Auditing
Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples. Empirical privacy auditing (EPA) quantifies this risk by measuring realistic data leak…
parameter-efficient fine-tuningEmpirical Privacy Variance
We propose the notion of empirical privacy variance and study it in the context of differentially private fine-tuning of language models. Specifically, we show that models calibrated to the same $(\varepsilon, \delta)$-D…
MemorizationAuditing Differential Privacy in the Black-Box Setting
This paper introduces a novel theoretical framework for auditing differential privacy (DP) in a black-box setting. Leveraging the concept of $f$-differential privacy, we explicitly define type I and type II errors and pr…
validDetecting Adversarial Fine-tuning with Auditing Agents
Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM can bypass safeguards. P…
Tight Auditing of Differentially Private Machine Learning
Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mechanisms are tight: the empirical privacy …
Federated Learning