PANORAMIA:无需重新训练的机器学习模型隐私审计
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
AI总结:
该研究提出 PANORAMIA 框架,利用生成数据作为非成员实施成员推理攻击,在不修改模型、数据或训练过程的前提下审计隐私泄露,并验证其适用于图像、表格分类模型及大规模语言模型。
摘要:
我们提出 PANORAMIA,这是一种面向机器学习模型的隐私泄露测量框架,它依赖成员推理攻击,并使用生成数据作为非成员。通过依赖生成的非成员数据,PANORAMIA 消除了隐私测量工具对同分布非成员数据的常见依赖。因此,PANORAMIA 不会修改模型、训练数据或训练过程,并且只需要访问训练数据的一个子集。我们在用于图像和表格数据分类的机器学习模型以及大规模语言模型上评估了 PANORAMIA。
英文摘要:
We present PANORAMIA, a privacy leakage measurement framework for machine learning models that relies on membership inference attacks using generated data as non-members. By relying on generated non-member data, PANORAMIA eliminates the common dependency of privacy measurement tools on in-distribution non-member data. As a result, PANORAMIA does not modify the model, training data, or training process, and only requires access to a subset of the training data. We evaluate PANORAMIA on ML models for image and tabular data classification, as well as on large-scale language models.
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。