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

Computer Science > Cryptography and Security [Submitted on 17 Jun 2026] Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning Ousmane Touat, César Sabater, Mohamed Maouche, Sonia Ben Mokhtar 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. Comments: 17 pages, with appendix Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2606.19129 [cs.CR]   (or arXiv:2606.19129v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.19129 Focus to learn more Submission history From: Ousmane Touat [view email] [v1] Wed, 17 Jun 2026 14:40:19 UTC (174 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)