一句话：提出 TeDA 测试框架，用边界搜索扰动构造 isotope 测试集并结合成员推断与假设检验，审计模型是否未经授权使用私有数据。
深度学习模型开发中未授权使用私有用户数据难以审计，即无法判断某模型是否在未经授权的情况下用特定用户数据训练或微调，而 GDPR、EU AI Act 等法规对数据透明性提出了迫切要求。本文提出 TeDA，一个简单灵活的 DL 数据使用审计测试框架。给定需保护的私有数据集 Dp，TeDA 以怀有善意的成员推断为核心，利用边界搜索引导的不可感知扰动，由 Dp 生成精心构造的测试集 Dt（称为 isotope），从而显著放大数据使用痕迹；随后结合成员推断与假设检验，在统计保证下判定私有数据是否被用于训练待审计模型 Ma。作者在多种数据规模与模型架构上，针对人脸识别和医疗诊断等敏感任务开展大量实验，验证了 TeDA 的高可行性、有效性与鲁棒性，包括在剪枝、蒸馏等自适应策略下的表现。
It is notoriously challenging to audit the potential unauthorized data usage in deep learning (DL) model development lifecycle, i.e., to judge whether certain private user data has been used to train or fine-tune a DL model without authorization. Yet, such data usage auditing is crucial to respond to the urgent requirements of trustworthy Artificial Intelligence (AI) such as data transparency, which are promoted and enforced in recent AI regulation rules or acts like General Data Protection Regulation (GDPR) and EU AI Act. In this work, we propose TeDA, a simple and flexible testing framework for auditing data usage in DL model development process. Given a set of user’s private data to protect (Dp), the intuition of TeDA is to apply membership inference (with good intention) for judging whether the model to audit (Ma) is likely to be trained with Dp. Notably, to significantly expose the usage under membership inference, TeDA applies imperceptible perturbation directed by boundary search to generate a carefully crafted test suite Dt (which we call ‘isotope’) based on Dp. With the test suite, TeDA then adopts membership inference combined with hypothesis testing to decide whether a user’s private data has been used to train Ma with statistical guarantee. We evaluated TeDA through extensive experiments on ranging data volumes across various model architectures for data-sensitive face recognition and medical diagnosis tasks. TeDA demonstrates high feasibility, effectiveness and robustness under various adaptive strategies (e.g., pruning and distillation).
DOI 原文 ·
@inproceedings{paperbot8538,
title = {TeDA: A Testing Framework for Data Usage Auditing in Deep Learning Model Development},
author = {Xiangshan Gao and Jialuo Chen and Jingyi Wang and Jie Shi and Peng Cheng and Jiming Chen},
booktitle = {ISSTA},
year = {2024},
doi = {10.1145/3650212.3680375}
}