论文标题
一项关于梯度反转的调查：攻击，防御和未来方向
A Survey on Gradient Inversion: Attacks, Defenses and Future Directions
论文作者
论文摘要
最近的研究表明，训练样本可以从梯度中回收，这些梯度称为梯度反转（Gradinv）攻击。但是，仍然缺乏广泛的调查，涵盖了最近的进步和对这个问题的彻底分析。在本文中，我们对Gradinv进行了全面的调查，旨在总结尖端研究并扩大不同领域的视野。首先，我们通过将现有攻击描述为两个范式：基于迭代和基于递归的攻击，提出了Gradinv攻击的分类法。特别是，我们从基于迭代的攻击中挖掘出一些关键成分，包括数据初始化，模型培训和梯度匹配。其次，我们总结了针对Gradinv攻击的新兴防御策略。我们发现这些方法集中在三种观点上，涵盖了数据晦涩，改进模型和梯度保护。最后，我们讨论了一些有希望的方向和开放问题，以进行进一步研究。
Recent studies have shown that the training samples can be recovered from gradients, which are called Gradient Inversion (GradInv) attacks. However, there remains a lack of extensive surveys covering recent advances and thorough analysis of this issue. In this paper, we present a comprehensive survey on GradInv, aiming to summarize the cutting-edge research and broaden the horizons for different domains. Firstly, we propose a taxonomy of GradInv attacks by characterizing existing attacks into two paradigms: iteration- and recursion-based attacks. In particular, we dig out some critical ingredients from the iteration-based attacks, including data initialization, model training and gradient matching. Second, we summarize emerging defense strategies against GradInv attacks. We find these approaches focus on three perspectives covering data obscuration, model improvement and gradient protection. Finally, we discuss some promising directions and open problems for further research.
