论文标题
在非IID数据上学习拜占庭式学习的线性标量
Linear Scalarization for Byzantine-robust learning on non-IID data
论文作者
论文摘要
在这项工作中，我们研究了客户之间的数据是异质的，拜占庭式学习的问题。我们专注于中毒攻击针对SGD收敛的攻击。尽管这个问题引起了极大的关注。拜占庭的主要防御依赖于IID假设，即使没有攻击，数据分布也是非IID时失败的。我们建议将线性标量（LS）用作增强方法，以使当前防御能够在非IID设置中绕开拜占庭式攻击。 LS方法是基于对可疑恶意客户处罚的权衡矢量的合并。经验分析证实了所提出的LS变体在IID设置中是可行的。对于轻度到强的非IID数据拆分，LS在最先进的拜占庭攻击场景下是可比或胜过当前方法。
In this work we study the problem of Byzantine-robust learning when data among clients is heterogeneous. We focus on poisoning attacks targeting the convergence of SGD. Although this problem has received great attention; the main Byzantine defenses rely on the IID assumption causing them to fail when data distribution is non-IID even with no attack. We propose the use of Linear Scalarization (LS) as an enhancing method to enable current defenses to circumvent Byzantine attacks in the non-IID setting. The LS method is based on the incorporation of a trade-off vector that penalizes the suspected malicious clients. Empirical analysis corroborates that the proposed LS variants are viable in the IID setting. For mild to strong non-IID data splits, LS is either comparable or outperforming current approaches under state-of-the-art Byzantine attack scenarios.
