# GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework

arXiv: https://arxiv.org/abs/2504.17471 · HTML: https://mlsanity.com/paper/2504.17471/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 68 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Builds on (most cited first, 30 of 33)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [A Unified Theory of Decentralized SGD with Changing Topology and Local Updates](https://mlsanity.com/paper/2003.10422/) (2020)
- [FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping](https://mlsanity.com/paper/2012.13995/) (2020)
- [Robust Aggregation for Federated Learning](https://mlsanity.com/paper/1912.13445/) (2019)
- [A Little Is Enough: Circumventing Defenses For Distributed Learning](https://mlsanity.com/paper/1902.06156/) (2019)
- [Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation](https://mlsanity.com/paper/1903.03936/) (2019)
- [Learning from History for Byzantine Robust Optimization](https://mlsanity.com/paper/2012.10333/) (2020)
- [Optimal algorithms for smooth and strongly convex distributed optimization in networks](https://mlsanity.com/paper/1702.08704/) (2017)
- [Interpretable Deep Learning under Fire](https://mlsanity.com/paper/1812.00891/) (2018)
- [Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity](https://mlsanity.com/paper/2302.01772/) (2023)
- [Exponential Graph is Provably Efficient for Decentralized Deep Training](https://mlsanity.com/paper/2110.13363/) (2021)
- [Byzantine-Robust Decentralized Federated Learning](https://mlsanity.com/paper/2406.10416/) (2024)
- [BRIDGE: Byzantine-resilient Decentralized Gradient Descent](https://mlsanity.com/paper/1908.08098/) (2019)
- [Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization](https://mlsanity.com/paper/2006.11773/) (2020)
- [ByRDiE: Byzantine-resilient distributed coordinate descent for decentralized learning](https://mlsanity.com/paper/1708.08155/) (2017)
- [Byzantine-Robust Decentralized Learning via ClippedGossip](https://mlsanity.com/paper/2202.01545/) (2022)
- [Approximate Byzantine Fault-Tolerance in Distributed Optimization](https://mlsanity.com/paper/2101.09337/) (2021)
- [Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging](https://mlsanity.com/paper/2206.05091/) (2022)
- [CrowdGuard: Federated Backdoor Detection in Federated Learning](https://mlsanity.com/paper/2210.07714/) (2022)
- [Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity](https://mlsanity.com/paper/2309.13591/) (2023)
- [Communication-Efficient Topologies for Decentralized Learning with O(1) Consensus Rate](https://mlsanity.com/paper/2210.07881/) (2022)
- [Byzantine-Resilient Decentralized Stochastic Optimization with Robust Aggregation Rules](https://mlsanity.com/paper/2206.04568/) (2022)
- [Byzantine-Tolerant Machine Learning](https://mlsanity.com/paper/1703.02757/) (2017)
- [Byzantine-Resilient Stochastic Gradient Descent for Distributed Learning: A Lipschitz-Inspired Coordinate-wise Median Approach](https://mlsanity.com/paper/1909.04532/) (2019)
- [Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks](https://mlsanity.com/paper/2209.04030/) (2022)
- [Unified Breakdown Analysis for Byzantine Robust Gossip](https://mlsanity.com/paper/2410.10418/) (2024)
- [SecureCyclon: Dependable Peer Sampling](https://mlsanity.com/paper/2309.02952/) (2023)

## Abstract (arXiv)

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.