Network Topology

Topology-Aware Differential Privacy in Hierarchical Federated Learning

Under Review

This work identifies hierarchical federated learning’s aggregation topology as a privacy channel orthogonal to DP-SGD, and derives a topology-aware noise allocation that provably matches uniform DP-SGD’s per-client privacy guarantee while recovering up to 88% of the noise budget.

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.