Received 7 August 2023, accepted 31 August 2023, date of publication 4 September 2023, date of current version 11 September 2023. Digital Object Identifier 10.1109/ACCESS.2023.3311822 A Collaborative DNN-Based Low-Latency IDPS for Mission-Critical Smart Factory Networks POULMANOGO ILLY 1 AND GEORGES KADDOUM 1,2 , (Senior Member, IEEE) 1 Electrical Engineering Department, École de Technologie Supérieure, Montreal, Quebec H3C 1K3, Canada 2 Cyber Security Systems and Applied AI Research Center, Lebanese American University, Beirut 1102, Lebanon Corresponding author: Poulmanogo Illy (poulmanogo.illy.1@ens.etsmtl.ca) This work was supported by NSERC under Grant B-CITI CRDPJ 501617-16. ABSTRACT Industrial Control Systems (ICSs) have entered an era of modernization enabled by the recent progress in Information Technologies (IT), particularly the Industrial Internet of Things (IIoT). This enables better automation of industrial processes but now exposes the ICSs to cyber-attacks that exploit the IIoT vulnerabilities. Thus, to ensure ICSs security, numerous research works have focused on designing Intrusion Detection and Prevention Systems (IDPSs), and deep learning has recently received considerable attention, as it has the potential to improve detection accuracy. However, most of the proposed deep learning solutions focus only on the model’s accuracy without considering latency, which is an essential requirement in many ICSs. The novelty of this paper is the time complexity analysis of Deep Neural Networks (DNNs) and the design of a low latency and robust deep learning-based collaborative IDPS. The proposed architecture employs two classification models. In the first model, a lightweight DNN is used to perform a binary classification, i.e., normal or attack, which ensures rapid intrusion detection. A second model ensures the identification of the type of attacks by performing a multi-class classification of the detected anomaly, which is handled by a robust and complex DNN in order to achieve higher accuracy. This research also proposes intrusion response measures to deal with detected attacks, first after the anomaly detection, and then after the identification of the attack type. An experimental evaluation has been provided using various detection features, datasets, DNN algorithms, and the results demonstrate the effectiveness of the proposed solution. INDEX TERMS Deep learning, industrial control system (ICS), industrial Internet of Things (IIoT), intrusion detection system (IDS), intrusion response system (IRS), network security, smart factory. I. INTRODUCTION Industrial facilities are usually highly delicate and risky envi- ronments, requiring maximum safety and security to work with potentially dangerous chemicals and tools, and pri- vacy to manufacture highly competitive products. Therefore, many security, safety, and privacy standards have been imple- mented over the years to protect these environments [1], [2], [3]. However, industrial accidents and disasters still occur fre- quently worldwide and cause significant damages, including deaths, injuries, economic losses, and long-term environ- mental impacts. According to the survey published in June 2021 by the research department of the database company Statista, there were 984 explosive incidents across the United The associate editor coordinating the review of this manuscript and approving it for publication was Varuna De Silva . States (USA) in 2020, which is a significant increase com- pared to previous years [4]. The sources of these explosions include manufacturing plants, electric utilities, petroleum industries (upstream, midstream, downstream, pipelines), and other chemical factories. The evolution of the industrial domain towards the new era of modernization driven by the Industrial Internet of Things (IIoT) enables real-time safety applications to prevent the traditional risk of inci- dents. However, it generates new security risks, notably from cyber-attacks that exploit the vulnerabilities of the connected objects. Unlike traditional standalone Industrial Control Systems (ICSs), which used to be isolated from Information and Communication Technology (ICT) networks, new ICSs inte- grate these networks to enable high-level process supervisory management. Indeed, thanks to connected sensors, actuators, VOLUME 11, 2023 This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ 96317