Special Issues
Table of Content

Applying AI Techniques for Cyber Physical Systems and Security Solutions: From Research to Practice

Submission Deadline: 01 November 2024 (closed) View: 643 Submit to Special Issue

Guest Editors

Dr. Mohammad Kamrul Hasan, Universiti Kebangsaan Malaysia, Malaysia
Dr. Nazmus Shaker Nafi, Boeing Defence Australia, Australia
Prof. Dr. Rashid A Saeed, Taif University, Saudi Arabia

Summary

Applying AI techniques in Cyber-Physical Systems (CPS) revolutionizes security solutions, intertwining digital and physical realms. By amalgamating AI's cognitive abilities with CPS's interconnectedness, robust defenses are forged against evolving threats. AI augments CPS by predicting anomalies, fortifying preemptive measures, and enabling adaptive responses, heightening system resilience. Machine learning algorithms decipher complex data streams within CPS, preempting breaches and orchestrating real-time adjustments, ensuring system integrity. AI-driven anomaly detection, coupled with proactive mitigation, fortifies CPS against vulnerabilities. Integrating AI in CPS safeguards infrastructures and fosters innovative solutions, propelling the synergy between artificial intelligence and cyber-physical systems toward a safer, more adaptive future.

 

Integrating AI in cyber-physical systems (CPS) poses promise and challenges. AI techniques optimize CPS operations but raise security concerns. Adversarial attacks leveraging AI vulnerabilities threaten system integrity, demanding robust defenses. Privacy breaches via AI-powered data analytics in CPS remain a concern, needing ethical guidelines. AI-driven decision-making in critical infrastructure may introduce biases or errors, impacting safety. Regulation gaps exist in governing AI-driven CPS, requiring standards for accountability. Balancing innovation and security is pivotal, necessitating ongoing research to fortify AI-enabled CPS against evolving threats. Collaboration among stakeholders is vital to establishing comprehensive strategies addressing the intricate intersection of AI and CPS security.

 

Cyber-Physical Systems (CPS) represent the integration of computational algorithms and physical components interconnected by networks. Ensuring these systems' security, reliability, and efficiency is paramount in today's technologically interconnected world. This special issue explores applying artificial intelligence (AI) techniques to address challenges and develop solutions for securing CPS.


Keywords

Topics of interest include but are not limited to:
·Multicasting program for establishing the path on the mobile ad hoc network
·AI-enabled threat detection and mitigation in CPS
·Machine learning approaches for anomaly detection in CPS
·AI-based intrusion detection and prevention systems
·Secure communication protocols for CPS using AI
·Predictive maintenance and fault detection in CPS through AI techniques
·Resilience and robustness of CPS against cyber-attacks
·Ethical and legal considerations in deploying AI for CPS security
·practical implementations and Case studies of AI in securing CPS
·Advances in data and cyber security on the Internet of Things (IoT)
·Fault tolerance program for implementing wireless sensor network

Published Papers


  • Open Access

    ARTICLE

    Classified VPN Network Traffic Flow Using Time Related to Artificial Neural Network

    Saad Abdalla Agaili Mohamed, Sefer Kurnaz
    CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 819-841, 2024, DOI:10.32604/cmc.2024.050474
    (This article belongs to the Special Issue: Applying AI Techniques for Cyber Physical Systems and Security Solutions: From Research to Practice)
    Abstract VPNs are vital for safeguarding communication routes in the continually changing cybersecurity world. However, increasing network attack complexity and variety require increasingly advanced algorithms to recognize and categorize VPN network data. We present a novel VPN network traffic flow classification method utilizing Artificial Neural Networks (ANN). This paper aims to provide a reliable system that can identify a virtual private network (VPN) traffic from intrusion attempts, data exfiltration, and denial-of-service assaults. We compile a broad dataset of labeled VPN traffic flows from various apps and usage patterns. Next, we create an ANN architecture that can… More >

Share Link