面向大语言模型中选择性遗忘隐私漏洞的基准测试
Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models
AI总结：
本文提出首个评估选择性遗忘隐私漏洞的基准，系统研究了反向学习技术的隐私漏洞，并为定制应用提供标准化工具。
摘要：
人工智能的快速发展主要集中在从数据中学习以获得知识学习系统的过程上。随着这些系统越来越多地应用于关键领域，确保其隐私性和与人类价值观的一致性至关重要。最近，选择性遗忘（也称为机器反向学习）在隐私和数据删除任务中显示出前景，并在人工智能领域成为变革性的范式转变。它指的是模型能够选择性地消除之前看到数据的影响，这对于遵守现代数据保护法规和使模型与人类价值观一致尤为重要。尽管有前景，选择性遗忘仍引发重大隐私问题，尤其是在涉及敏感领域数据时。虽然新的反向学习诱导隐私攻击不断被提出，但每种攻击都通过不同的实验设置显示出优于其前代攻击，这可能导致过于乐观且可能不公平的评估，可能使某种攻击相对于其他攻击具有偏见。在本工作中，我们提出了第一个全面的基准，用于评估选择性遗忘中的隐私漏洞。我们广泛研究了机器反向学习技术的隐私漏洞，并在广泛的受害者数据、最先进的反向学习隐私攻击、反向学习方法和模型架构上基准测试隐私泄露。我们系统地评估并识别了与反向学习诱导隐私泄露相关的关键因素。通过我们的新见解，我们旨在为寻求部署定制反向学习应用的实践者提供标准化工具，以实现忠实的隐私评估。
英文摘要：
The rapid advancements in artificial intelligence (AI) have primarily focused on the process of learning from data to acquire knowledgeable learning systems. As these systems are increasingly deployed in critical areas, ensuring their privacy and alignment with human values is paramount. Recently, selective forgetting (also known as machine unlearning) has shown promise for privacy and data removal tasks, and has emerged as a transformative paradigm shift in the field of AI. It refers to the ability of a model to selectively erase the influence of previously seen data, which is especially important for compliance with modern data protection regulations and for aligning models with human values. Despite its promise, selective forgetting raises significant privacy concerns, especially when the data involved come from sensitive domains. While new unlearning-induced privacy attacks are continuously proposed, each is shown to outperform its predecessors using different experimental settings, which can lead to overly optimistic and potentially unfair assessments that may disproportionately favor one particular attack over the others. In this work, we present the first comprehensive benchmark for evaluating privacy vulnerabilities in selective forgetting. We extensively investigate privacy vulnerabilities of machine unlearning techniques and benchmark privacy leakage across a wide range of victim data, state-of-the-art unlearning privacy attacks, unlearning methods, and model architectures. We systematically evaluate and identify critical factors related to unlearning-induced privacy leakage. With our novel insights, we aim to provide a standardized tool for practitioners seeking to deploy customized unlearning applications with faithful privacy assessments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
