SoK：机器学习系统中的数据集版权审计
SoK: Dataset Copyright Auditing in Machine Learning Systems
AI总结：
本文系统化梳理了机器学习数据集版权审计的侵入式与非侵入式方法，比较其优缺点，并指出未来方向以提升实际部署中的版权保护效果。
摘要：
随着机器学习（ML）系统的实施日益广泛，尤其是随着更大规模ML模型的引入，我们感知到对海量数据的迫切需求。然而，这不可避免地导致了数据侵权和滥用问题，例如使用未经授权的在线艺术作品或人脸图像来训练ML模型。为了解决这一问题，许多工作致力于审计模型训练数据集的版权。然而，现有解决方案在审计假设和能力上各不相同，使得比较其优缺点变得困难。此外，鲁棒性评估通常只考虑ML流水线的一部分，难以反映算法在真实世界ML应用中的性能。因此，从实际部署的角度审视当前的数据集版权审计工具，考察其有效性和局限性至关重要。具体而言，我们将数据集版权审计研究分为两大主要方向：侵入式方法和非侵入式方法，取决于它们是否需要对原始数据集进行修改。然后，我们将侵入式方法细分为不同的水印注入选项，并使用各种指纹检查非侵入式方法。为总结我们的结果，我们提供了详细的参考表，突出关键点，并指出现有文献中未解决的问题。通过结合ML系统中的流水线并分析先前研究，我们强调了几个未来方向，以使审计工具更适应真实世界的版权保护需求。
英文摘要：
As the implementation of machine learning (ML) systems becomes more widespread, especially with the introduction of larger ML models, we perceive a spring demand for massive data. However, it inevitably causes infringement and misuse problems with the data, such as using unauthorized online artworks or face images to train ML models. To address this problem, many efforts have been made to audit the copyright of the model training dataset. However, existing solutions vary in auditing assumptions and capabilities, making it difficult to compare their strengths and weaknesses. In addition, robustness evaluations usually consider only part of the ML pipeline and hardly reflect the performance of algorithms in real-world ML applications. Thus, it is essential to take a practical deployment perspective on the current dataset copyright auditing tools, examining their effectiveness and limitations. Concretely, we categorize dataset copyright auditing research into two prominent strands: intrusive methods and non-intrusive methods, depending on whether they require modifications to the original dataset. Then, we break down the intrusive methods into different watermark injection options and examine the non-intrusive methods using various fingerprints. To summarize our results, we offer detailed reference tables, highlight key points, and pinpoint unresolved issues in the current literature. By combining the pipeline in ML systems and analyzing previous studies, we highlight several future directions to make auditing tools more suitable for real-world copyright protection requirements.
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。
