cs.LGNov 12, 2026

Class-Competence Aggregation: Output-Layer Routing for Federated Multiclass DDoS Detection under Class-Concentrated Non-IID Data

Authors: Tapu Datta, Hafiz Imtiaz

Organizations: Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka 1205, Bangladesh

Abstract

Federated learning over distributed intrusion-detection sensors naturally produces class-concentrated non-IID data, where an entire attack class is held by a single client and absent elsewhere. We show this collapses federated averaging in a specific, localized way: the output layer holds one decision boundary per class, and when a class's aggregation weight comes overwhelmingly from clients that have never seen it, its neuron receives an active anti-signal rather than mere dilution, collapsing to zero. On CIC-DDoS2019, standard FedAvg drives the concentrated LDAP class to 0.00±0.00%0.00 \pm 0.00\% F1 across every seed. We propose Class-Competence Aggregation (CCA), which aggregates the output layer per class using each client's own locally reported validation F1 as the weight, while hidden layers remain under standard size-weighted FedAvg. CCA requires no server-held auxiliary data and adds only one F1 scalar per class per round beyond the feature-scaling and class-count exchanges common to any federated pipeline. On our primary CNN-LSTM architecture, CCA alone raises LDAP F1 from 0%0\% to 84.83±1.65%84.83 \pm 1.65\%, and the full method reaches 91.64±0.57%91.64 \pm 0.57\% macro F1, closing the federated-to-centralized gap from −42.53-42.53 to −4.05-4.05 points. Benchmarked against four other federated methods under identical partitions and seeds, CCA is the only one that recovers the concentrated class substantially and reliably; a 178×178\times smaller MLP shows the same qualitative recovery, though less completely, confirming the effect holds across architecture scale even as its magnitude varies. Results are validated across three seeds and replicated on a second dataset, CICIDS2017.

Figures & tables

Explore similar work

CardsList
  1. Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface

    Sep 3, 2026Adrita Rahman Tory, ABM Shawkat Ali, Md Abu Layek +1Class-Imbalanced LearningFederated Learning Aggregation

  2. BRFID: Toward Byzantine-Robust Federated Intrusion Detection

    Sep 23, 2026Asmah Muallem, Firdous Kausar, Sajid Hussain +1Byzantine-Robust Federated LearningAdversarial Attacks

  3. CALM: Class-wise Agreement and Label-gated Disagreement Modulation for Decentralized Federated Learning

    Sep 5, 2026Yifan Ying, Qing TianFederated Knowledge DistillationTrust-Aware Federated Learning