arXiv cs.AI· Saheed A. Tijani, Frank Jiang, Ming Liu·· 12 小时前AI 评分22
LiBRA：用 Logit 指纹实现联邦学习中的拜占庭鲁棒客户端选择
LiBRA: Logit Fingerprints for Byzantine-Robust Client Selection in Federated Learning
AI 导读
LiBRA 提出用模型对伪模式产生的类条件 logit 响应（C 个类别共 C² 个值）作为客户端指纹，替代参数向量做拜占庭鲁棒聚合中的相似度比较。基于该指纹改造的 Krum、Multi-Krum 和 Bulyan 变体在 Fashion-MNIST 与 CIFAR-10 上保持原方法的全部防御能力，后门攻击下恶意客户端排序与全参数向量的 AUC 差距在 0.006 以内。
正文 · 原文
Abstract:Byzantine-robust aggregation shields federated learning from malicious updates, but the rules that filter out suspect updates do so by comparing clients' parameter vectors. That comparison requires access to every client's update, which secure aggregation exists to withhold, costs $O(n^2 d)$ in the parameter dimension $d$, and is defined only between clients that share an architecture. We propose LiBRA, which compares clients on what their models compute rather than on the parameters that compute them, using a fingerprint of $C^2$ values for $C$ classes, the class-conditional logit response of each client's model to pseudo-patterns optimised against it. We instantiate LiBRA as variants of Krum, Multi-Krum and Bulyan that change only what the dissimilarity score is computed on. On Fashion-MNIST and CIFAR-10 with three architectures and four backdoor and label-manipulation attacks under i.i.d. partitions, each variant holds every attack its parent holds, and on identical client updates under a backdoor attack the fingerprint ranks malicious clients within 0.006 AUC of the full parameter vector. The variants thus match the robustness of the rules they extend, while their trust decision reads no client parameter, compares up to 49,090 times fewer values, and can by construction compare clients whose architectures differ, at the cost of one pattern optimisation per client per round.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.27357 [cs.LG] |
| (or arXiv:2610.27357v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27357 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Saheed Tijani [view email]
[v1]
Mon, 19 Oct 2026 22:35:44 UTC (368 KB)
来源：arXiv cs.AI · arxiv.org