mlsanityData to 14 Oct 2026

Spectral Sentinel: Scalable Byzantine-Robust Decentralized Federated Learning via Sketched Random Matrix Theory on Blockchain

arXiv 2512.12617 ↗First posted 14 Dec 2025cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Decentralized federated learning (DFL) enables collaborative model training without centralized trust, but it remains vulnerable to Byzantine clients that poison gradients under heterogeneous (Non-IID) data. Existing defenses face a scalability trilemma: distance-based filtering (e.g., Krum) can reject legitimate Non-IID updates, geometric-median methods incur prohibitive O(n2 d) cost, and many certified defenses are evaluated only on models below 100M parameters. We propose Spectral Sentinel, a Byzantine detection and aggregation framework that leverages a random-matrix-theoretic signature: honest Non-IID gradients produce covariance eigenspectra whose bulk follows the Marchenko-Pastur law, while Byzantine perturbations induce detectable tail anomalies. Our algorithm combines Frequent Directions sketching with data-dependent MP tracking, enabling detection on models up to 1.5B parameters using O(k2) memory with k ll d. Under a (σ,f) threat model with coordinate-wise honest variance bounded by σ2 and f < 1/2 adversaries, we prove (ε,δ)-Byzantine resilience with convergence rate O(σ f / √T + f2 / T), and we provide a matching information-theoretic lower bound Omega(σ f / √T), establishing minimax optimality. We implement the full system with blockchain integration on Polygon networks and validate it across 144 attack-aggregator configurations, achieving 78.4 percent average accuracy versus 48-63 percent for baseline methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 14 Dec 2025.

Builds on

18 of 35 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  4. 2018Federated Learning with Non-IID Datacited by 1,108
  5. 2018LEAF: A Benchmark for Federated Settingscited by 792
  6. 2018How To Backdoor Federated Learningcited by 765
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  8. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  9. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  10. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  11. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  12. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
6 more
  1. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
  2. 2014Sketching as a Tool for Numerical Linear Algebracited by 288
  3. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  4. 2017Gradient Sparsification for Communication-Efficient Distributed Optimizationcited by 201
  5. 2018Mitigating Sybils in Federated Learning Poisoningcited by 161
  6. 2017Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practicecited by 132

Built on by

Not cited yet.