探索黑白盒DNN叛徒追踪的联邦学习动态
Exploring Federated Learning Dynamics for Black-and-White-Box DNN Traitor Tracing
AI总结：
本文研究联邦学习分类器中的黑白盒叛徒追踪水印，发现白盒指纹抗泄露而黑盒指纹失效，并提出通过dropout正则化增加显著神经元以恢复黑盒追踪能力，证明在FL中实现抗合谋叛徒追踪可行。
摘要：
随着深度学习应用日益普及，对大量训练样本的需求引发了对敏感、个人或专有数据的担忧。为克服这一问题，联邦学习（FL）支持跨分布式数据所有者进行协作模型训练，但它在保护模型所有权以及在发生泄露时识别来源方面带来了挑战。在先前工作的基础上，本文探索了将黑白叛徒追踪水印适配到FL分类器的方法，以应对来自不同数据所有者的合谋攻击威胁。本研究表明，抗泄露的白盒指纹可以直接实现，且不受FL动态的显著影响，而黑盒指纹则受到剧烈影响，丧失了其叛徒追踪能力。为减轻这一影响，我们提出通过dropout正则化增加黑盒显著神经元的数量。尽管仍有一些待探索的开放问题，例如分析非独立同分布数据集和过参数化模型，但结果表明，即使在训练的早期阶段，抗合谋的叛徒追踪——识别涉嫌泄露中涉及的所有数据所有者——在FL框架中是可行的。
英文摘要：
As deep learning applications become more prevalent, the need for extensive training examples raises concerns for sensitive, personal, or proprietary data. To overcome this, Federated Learning (FL) enables collaborative model training across distributed data-owners, but it introduces challenges in safeguarding model ownership and identifying the origin in case of a leak. Building upon prior work, this paper explores the adaptation of black-and-white traitor tracing watermarking to FL classifiers, addressing the threat of collusion attacks from different data-owners. This study reveals that leak-resistant white-box fingerprints can be directly implemented without a significant impact from FL dynamics, while the black-box fingerprints are drastically affected, losing their traitor tracing capabilities. To mitigate this effect, we propose increasing the number of black-box salient neurons through dropout regularization. Though there are still some open problems to be explored, such as analyzing non-i.i.d. datasets and over-parameterized models, results show that collusion-resistant traitor tracing, identifying all data-owners involved in a suspected leak, is feasible in an FL framework, even in early stages of training.
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。
