paper-with-me

홈 › Papers

On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models

2024-11-11 · Qian Sun, Hanpeng Wu, Xi Sheryl Zhang

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/.

📄 PDF Abstract BibTeX arXiv:2411.07070

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Advancing the State-of-the-Art in Empirical Privacy Auditing

2026-06-09 · Nicole Mitchell, Galen Andrew, Arun Ganesh, Brendan McMahan 외 arxiv

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-tuning

Empirical Privacy Variance

2025-03-16 · Yuzheng Hu, Fan Wu, Ruicheng Xian, Yuhang Liu 외

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…

Memorization

Auditing Differential Privacy in the Black-Box Setting

2025-03-15 · Kaining Shi, Cong Ma

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…

valid

Detecting Adversarial Fine-tuning with Auditing Agents

2025-10-17 · Sarah Egler, John Schulman, Nicholas Carlini arxiv

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

2023-02-15 · Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle 외

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