Network Topology

Trust-Aware Topology Learning for Dynamic Decentralized Federated Learning under Adversaries

Under Review

This work shows that in decentralized learning, adversaries can attack the collaboration topology itself, not just model updates, and introduces DMTT, a trust-screened aggregation protocol that provably bounds Byzantine influence while empirically matching no-attack accuracy across mobile sensing benchmarks where existing robust aggregators collapse.

Topology-Aware Differential Privacy in Federated Learning

Under Review

This work identifies federated learning’s communication topology as a privacy channel orthogonal to DP-SGD, and derives a topology-aware noise allocation that provably dominates uniform DP-SGD on the per-client leakage bound at no measurable utility cost.