提出抗拜占庭攻击的动态通信框架，让分布式学习更安全高效
GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework
- 通过追踪节点标识动态调整聚合阈值，识别并抑制恶意节点
- 在30%恶意节点下仍保持接近正常精度的5%以内，通信开销降低9倍
- 适合高风险分布式场景，如物联网、区块链等去中心化系统
Gossip Learning（GL）是一种去中心化学习范式，用户通过与少量邻居节点迭代交换和聚合模型。现有方法依赖基于随机对等采样（RPS）协议构建的动态通信图，已被证明可加速收敛。然而，我们发现这些方法易受双重攻击：拜占庭节点可污染模型并操纵对等采样以放大其影响。为此，我们提出GRANITE框架，实现稀疏动态图上对抗拜占庭节点的鲁棒学习。GRANITE通过长期积累节点标识信息，根据每个节点邻域内估计的拜占庭密度动态调整本地聚合阈值。我们证明，在GRANITE下，局部邻域中的拜占庭存在呈指数衰减。进一步推导了由GRANITE生成图的鲁棒性条件。实验证明，当存在30%拜占庭节点时，GRANITE仍能收敛至非拜占庭准确率的5%以内，且收敛更快，通信成本比基准降低9倍。
原文摘要 · Abstract (English)
Gossip Learning (GL) is a decentralized learning paradigm where users iteratively exchange and aggregate models with a small set of neighboring peers. Recent approaches rely on dynamic communication graphs built using Random Peer Sampling (RPS) protocols which have been proven to accelerate convergence. However, we show that these approaches are vulnerable to a dual attack: Byzantine nodes can poison models and manipulate peer sampling to amplify their influence. We address this combination of threats with GRANITE, a framework for robust learning over sparse, dynamic graphs in the presence of Byzantine nodes. GRANITE accumulates knowledge about encountered node identifiers over time and dynamically adjusts local aggregation thresholds based on estimated Byzantine density in the neighbourhood of each node. We demonstrate that under GRANITE, the Byzantine presence in local neighborhoods exhibits an exponential decay. We further derive the robustness conditions of the graphs generated by GRANITE. Empirically, our results indicate that GRANITE converges within 5% of non-Byzantine accuracy under 30% Byzantines nodes, offers faster convergence and operates on graphs with up to 9x lower communication cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。