Spectral Sentinel: Scalable Byzantine-Robust Decentralized Federated Learning via Sketched Random Matrix Theory on Blockchain
This addresses the scalability and robustness issues in decentralized federated learning for applications requiring trustless collaboration, though it is an incremental improvement over existing defenses.
The paper tackles the vulnerability of decentralized federated learning to Byzantine clients under heterogeneous data by proposing Spectral Sentinel, a detection and aggregation framework that uses random-matrix-theoretic signatures to identify anomalies, achieving 78.4% average accuracy in validation tests.
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 $O(n^2 d)$ 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 $O(k^2)$ memory with $k \ll d$. Under a $(σ,f)$ threat model with coordinate-wise honest variance bounded by $σ^2$ and $f < 1/2$ adversaries, we prove $(ε,δ)$-Byzantine resilience with convergence rate $O(σf / \sqrt{T} + f^2 / T)$, and we provide a matching information-theoretic lower bound $Ω(σf / \sqrt{T})$, 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.