Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning

• URL: http://arxiv.org/abs/2606.19129v1
• Date: Wed, 17 Jun 2026 14:40:19 GMT
• Title: Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning
• Abstract summary: We present Giskard, a protocol for confidential and Byzantine-robust decentralized aggregation.<n>Giskard reduces per-party communication complexityally while exhibiting comparable model utility under up to $n/4$ Byzantine parties.
• Score: 1.9465112504866975
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem. Indeed, in decentralized learning, clients train a machine learning model while keeping their data locally and share their model parameters or gradients with a set of neighbors. While enforcing confidentiality calls for hiding the exchanged model parameters/gradients (e.g., by using cryptographic techniques), dealing with Byzantine contributions often requires inspecting the latter. Hence, most research works address these objectives separately. A recent line of work proposes to employ secure multi-party computation (MPC) to implement robust aggregators against model poisoning, thereby enforcing both confidentiality and Byzantine resilience. However, these solutions scale badly: they either require all-to-all communication between participants or delegate the entire computation to a small subset, whose computational and communication load grows proportionally with the size of the network. In this paper, we present Giskard, a protocol for confidential and Byzantine-robust decentralized aggregation. Giskard organizes $n$ parties into a tree of committees of size $O(\log n)$ and evaluates a coordinate-wise approximate median via a committee-adapted distributed binary search over the value domain, using BGW-style MPC within each committee. We assess Giskard both theoretically by proving its security and confidentiality properties and experimentally through extensive experiments involving up to one million participants. Compared to its closest competitors, Giskard reduces per-party communication complexity asymptotically while exhibiting comparable model utility under up to $n/4$ Byzantine parties.

Related papers

• Differentially private federated learning with Byzantine-robust aggregation: A cross-domain framework for secure model training in banking and healthcare systems [0.0]
  Federated learning allows regulated organizations to train a shared model without moving raw records off their own servers.<n>Two problems limit how far this promise can be trusted in practice.<n>A Byzantine-robust aggregator with no privacy layer performs best in raw accuracy.
  arXiv  Detail & Related papers  (2026-09-02T18:36:30Z)
• DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication [71.60998478544028]
  We propose Differentially Private Gradient Push with Compressed communication (termedfrac-CSGP) for decentralized learning graphs.<n>For general non-math and smooth objective functions, we show that our algorithm is designed to maintain high accuracy and efficient communication.
  arXiv  Detail & Related papers  (2025-12-15T17:37:02Z)
• Robust and Efficient Collaborative Learning [11.2807237249719]
  Collaborative machine learning is challenged by training-time adversarial behaviors.<n>We propose Robust Pull-based Epidemic Learning (RPEL) to ensure robust learning despite adversaries.
  arXiv  Detail & Related papers  (2025-10-09T14:57:29Z)
• Perfectly-Private Analog Secure Aggregation in Federated Learning [51.61616734974475]
  In federated learning, multiple parties train models locally and share their parameters with a central server, which aggregates them to update a global model.<n>In this paper, a novel secure parameter aggregation method is proposed that employs the torus rather than a finite field.
  arXiv  Detail & Related papers  (2025-09-10T15:22:40Z)
• Information-Theoretic Decentralized Secure Aggregation with Collusion Resilience [95.33295072401832]
  We study the problem of decentralized secure aggregation (DSA) from an information-theoretic perspective.<n>We characterize the optimal rate region, which specifies the minimum achievable communication and secret key rates for DSA.<n>Our results establish the fundamental performance limits of DSA, providing insights for the design of provably secure and communication-efficient protocols.
  arXiv  Detail & Related papers  (2025-08-01T12:51:37Z)
• Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts [8.700087812420687]
  We provide guarantees for the model's performance on a different, unseen network "B"<n>We show how the principled vanilla DKW bound enables certification of the model's true performance on unseen clients within the same (source) network.
  arXiv  Detail & Related papers  (2024-10-26T18:45:15Z)
• On the Necessity of Collaboration for Online Model Selection with Decentralized Data [53.244188985271606]
  We consider online model selection with decentralized data over $M$ clients, and study the necessity of collaboration among clients. Our results show (i) collaboration is unnecessary in the absence of computational constraints on clients; (ii) collaboration is necessary if the computational cost on each client is limited to $o(K)$, where $K$ is the number of candidate hypothesis spaces.
  arXiv  Detail & Related papers  (2024-04-15T06:32:28Z)
• BRFL: A Blockchain-based Byzantine-Robust Federated Learning Model [8.19957400564017]
  Federated learning, which stores data in distributed nodes and shares only model parameters, has gained significant attention for addressing this concern. A challenge arises in federated learning due to the Byzantine Attack Problem, where malicious local models can compromise the global model's performance during aggregation. This article proposes the integration of Byzantine-Robust Federated Learning (BRLF) model that combines federated learning with blockchain technology.
  arXiv  Detail & Related papers  (2023-10-20T10:21:50Z)
• Federated Stochastic Approximation under Markov Noise and Heterogeneity: Applications in Reinforcement Learning [24.567125948995834]
  Federated reinforcement learning is a framework in which $N$ agents collaboratively learn a global model. We show that by careful collaboration of the agents in solving this joint fixed point problem, we can find the global model $N$ times faster.
  arXiv  Detail & Related papers  (2022-06-21T08:39:12Z)
• Federated Stochastic Primal-dual Learning with Differential Privacy [15.310299472656533]
  We propose a new federated primal-dual algorithm with differential privacy (FedSPDDP) Our analysis shows that the data sampling strategy and PCP can enhance the data privacy whereas the larger number of local SGD steps could increase privacy leakage. Experiment results are presented to evaluate the practical performance of the proposed algorithm.
  arXiv  Detail & Related papers  (2022-04-26T13:10:37Z)
• Byzantine-Robust Decentralized Learning via ClippedGossip [61.03711813598128]
  We propose a ClippedGossip algorithm for Byzantine-robust consensus optimization. We demonstrate the encouraging empirical performance of ClippedGossip under a large number of attacks.
  arXiv  Detail & Related papers  (2022-02-03T12:04:36Z)
• Secure Distributed Training at Scale [65.7538150168154]
  Training in presence of peers requires specialized distributed training algorithms with Byzantine tolerance. We propose a novel protocol for secure (Byzantine-tolerant) decentralized training that emphasizes communication efficiency.
  arXiv  Detail & Related papers  (2021-06-21T17:00:42Z)
• Coded Stochastic ADMM for Decentralized Consensus Optimization with Edge Computing [113.52575069030192]
  Big data, including applications with high security requirements, are often collected and stored on multiple heterogeneous devices, such as mobile devices, drones and vehicles. Due to the limitations of communication costs and security requirements, it is of paramount importance to extract information in a decentralized manner instead of aggregating data to a fusion center. We consider the problem of learning model parameters in a multi-agent system with data locally processed via distributed edge nodes. A class of mini-batch alternating direction method of multipliers (ADMM) algorithms is explored to develop the distributed learning model.
  arXiv  Detail & Related papers  (2020-10-02T10:41:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.