Cybersecurity in Edge Computing: A Trust-Aware Federated Hybrid Intrusion Detection Framework
Researchers propose a trust-aware federated hybrid IDS that detects edge attacks without sharing raw telemetry.
The paper proposes TA-FHIDF, a federated intrusion-detection system for resource-constrained edge and IoT devices. A local engine combining an autoencoder, 1D-CNN, and BiLSTM extracts spatial and temporal features while raw telemetry stays at the gateway. A server-side trust score based on cosine similarity filters client updates before aggregation to resist model poisoning. The authors report strong accuracy, fast convergence, and Byzantine tolerance on UNSW-NB15, CICIDS2017, and Edge-IIoTset.
- Combines an autoencoder, 1D-CNN, and BiLSTM for local detection.
- Federated training keeps raw network telemetry on edge gateways.
- Cosine-similarity aggregation is meant to reject poisoned client updates.
- Evaluated on UNSW-NB15, CICIDS2017, and Edge-IIoTset.
From the original article
1 min read at arxiv.orgEdge computing has emerged as a critical computing paradigm in modern distributed systems by migrating data processing closer to end users and Internet of Things (IoT) devices. While this paradigm decentralizes processes, minimizes latency, and reduces backhaul bandwidth congestion, it exponentially enlarges the cyberattack surface.
By Zawad Yalmie Sazid · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.