Reproducibility Package for "Federated Learning-enabled Intrusion Detection System (FL-IDS) with Differential Privacy for Resource-Constrained IoT Networks"

Abstract

This repository contains the source code, executed notebook, experimental configurations, seed-level results, privacy-accounting outputs, clipping diagnostics, preprocessing metadata and supporting materials for the study “Federated Learning-enabled Intrusion Detection System (FL-IDS) with Differential Privacy for Resource-Constrained IoT Networks.” The package supports reproduction of the official UNSW-NB15 federated benchmark and the duplicate-safe full-corpus evaluation described in the manuscript. The original UNSW-NB15 dataset is not redistributed. File names, SHA-256 hashes, preprocessing procedures, model-training seeds and privacy-accounting assumptions are provided to support independent reproduction.