{"ID":2837862,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18240","arxiv_id":"2511.18240","title":"Carbon-Aware Intrusion Detection: A Comparative Study of Supervised and Unsupervised DRL for Sustainable IoT Edge Gateways","abstract":"The rapid expansion of the Internet of Things (IoT) has intensified cybersecurity challenges, particularly in mitigating Distributed Denial-of-Service (DDoS) attacks at the network edge. Traditional Intrusion Detection Systems (IDSs) face significant limitations, including poor adaptability to evolving and zero-day attacks, reliance on static signatures and labeled datasets, and inefficiency on resource-constrained edge gateways. Moreover, most existing DRL-based IDS studies overlook sustainability factors such as energy efficiency and carbon impact. To address these challenges, this paper proposes two novel Deep Reinforcement Learning (DRL)-based IDS: DeepEdgeIDS, a label-free Autoencoder-DRL hybrid, and AutoDRL-IDS, a supervised LSTM--DRL model. Both DRL-based IDS are validated through theoretical analysis and experimental evaluation on edge gateways. Results demonstrate that AutoDRL-IDS achieves 94% detection accuracy using labeled data, while DeepEdgeIDS attains 98% offline evaluation accuracy through label-free anomaly detection and online mitigation feedback. This study introduces a carbon-aware, multi-objective reward formulation that supports supervised reward optimization for AutoDRL-IDS and label-free online reward learning for DeepEdgeIDS, enabling sustainable real-time IDS operation in dynamic IoT networks.","short_abstract":"The rapid expansion of the Internet of Things (IoT) has intensified cybersecurity challenges, particularly in mitigating Distributed Denial-of-Service (DDoS) attacks at the network edge. Traditional Intrusion Detection Systems (IDSs) face significant limitations, including poor adaptability to evolving and zero-day att...","url_abs":"https://arxiv.org/abs/2511.18240","url_pdf":"https://arxiv.org/pdf/2511.18240v2","authors":"[\"Saeid Jamshidi\",\"Foutse Khomh\",\"Kawser Wazed Nafi\",\"Amin Nikanjam\",\"Samira Keivanpour\",\"Omar Abdul-Wahab\",\"Martine Bellaiche\"]","published":"2025-11-23T00:59:27Z","proceeding":"cs.CR","tasks":"[\"cs.CR\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}