Kamal Acharya

Postdoctoral Research Associate at Baylor University

Back to Publications

Journal Article

Quantum AI-Enhanced IoT-Fog Communication: A Survey From Cybersecurity and Data Privacy Perspective

By Antônio Roberto Lins de Macêdo Senthil Kumar Jagatheesaperumal Kelton Augusto Pontara da Costa Kamal Acharya Houbing Herbert Song Mohsen Guizani Victor Hugo C. de Albuquerque

An IEEE Communications Surveys & Tutorials article on Quantum AI for cybersecurity and data privacy in next-generation IoT-Fog communication, 6G services, industrial systems, and cyber-physical infrastructure.

2026 IEEE Communications Surveys & Tutorials DOI: 10.1109/COMST.2025.3622378

Quantum AI IoT Cybersecurity

DOI Publisher Page Cite

Abstract

The need for data privacy in the next-generation communication networks encompassing the Internet of Things (IoT) and Fog infrastructure has become very significant. This enforces the need for Quantum Artificial Intelligence (AI) approaches to safeguard them. The evolving new means of threats, which are complex and challenging to predict, make conventional security solutions difficult to address and mitigate. To counteract them proactively and efficiently, most organizations have started using AI solutions, which analyze and predict patterns of threats. However, most recent threats demand more robust solutions integrated into the network infrastructure. To sort out most of the demands of IoT-Fog communication services, we present a comprehensive review of Quantum AI to provide a secure and robust framework. Specifically, we provide a taxonomy to summarize the studies on Quantum AI over the IoT-Fog infrastructure, intended to provide predictive maintenance, mitigating threats, and robust defense strategies. Furthermore, we propose the integration of Neurosymbolic AI, which combines the pattern recognition power of neural networks with the reasoning capabilities of symbolic systems, thereby enabling context-aware threat detection and explainable decision-making in critical infrastructure security. In addition, we also emphasize network protocol security and communication privacy issues, particularly in industrial and cyber-physical system networks. Finally, we discuss prominent research challenges and open-ended future research directions for Quantum AI in next-generation wireless networks.

In brief

What This Work Does

This paper looks at how Quantum AI can strengthen privacy and security for connected devices and fog computing systems, especially where cyber-physical infrastructure needs fast and explainable threat detection.

Research impact

Why It Matters

IoT-Fog communication systems increasingly support healthcare, smart cities, industrial automation, transportation, energy systems, and 6G services. These environments process sensitive data close to the edge while facing evolving cyber threats. This survey explains how Quantum AI, post-quantum security, and neurosymbolic reasoning can contribute to more adaptive, explainable, and privacy-aware cybersecurity for distributed infrastructure.

Paper at a glance

Research Scope

4Research stages
5Methods or application areas
8Future research directions

Quantum AI Security Framework for IoT-Fog Communication

1

Threat Detection

Uses Quantum AI and machine learning to identify anomalies, intrusions, and complex attack patterns across decentralized IoT-Fog networks.

2

Privacy Protection

Addresses secure data transmission, communication privacy, quantum key distribution, and post-quantum cryptographic protection for sensitive edge data.

3

Explainable Cyber Defense

Integrates neurosymbolic AI to make threat detection more context-aware, interpretable, and useful for cybersecurity operators.

4

Resilient Infrastructure

Focuses on industrial systems, cyber-physical networks, 6G communication, real-time monitoring, and robust defense strategies.

Key Contributions

  • Surveys Quantum AI techniques for IoT-Fog cybersecurity and data privacy.
  • Builds a taxonomy of studies across threat mitigation, predictive maintenance, and robust defense.
  • Highlights neurosymbolic AI as a route toward context-aware and explainable security decisions.
  • Identifies open challenges for Quantum AI in next-generation wireless and cyber-physical networks.

Modeling Approaches Reviewed

Quantum Machine Learning

Applies quantum-enhanced learning models such as quantum neural networks and quantum support vector machines for cybersecurity analytics.

Post-Quantum Cryptography

Prepares IoT-Fog systems for quantum-era threats by replacing vulnerable classical cryptography with quantum-resistant protocols.

Quantum Key Distribution

Supports secure communication channels that are resistant to traditional eavesdropping attacks.

Neurosymbolic AI

Combines neural pattern recognition with symbolic reasoning to improve explainability and context-aware threat detection.

Federated and Edge Intelligence

Supports distributed learning and local decision-making across resource-constrained fog nodes and IoT devices.

Research Gaps

  1. 6G security
  2. Fog-node scalability
  3. Quantum hardware limits
  4. Efficient data encoding
  5. PQC migration
  6. Real-time processing
  7. Model interpretability
  8. Adversarial robustness

Publication Details

Type
Journal Article
Venue
IEEE Communications Surveys & Tutorials
Year
2026
Volume
28
Pages
3637-3665

Research Topics

Quantum AI IoT Cybersecurity

Citation

@article{deMacedo2026quantum,
  author={de Macêdo, Antônio Roberto L. and Jagatheesaperumal, Senthil Kumar and da Costa, Kelton Augusto Pontara and Acharya, Kamal and Song, Houbing and Guizani, Mohsen and de Albuquerque, Victor Hugo C.},
  title={Quantum AI-Enhanced IoT-Fog Communication: A Survey From Cybersecurity and Data Privacy Perspective},
  journal={IEEE Communications Surveys & Tutorials},
  year={2026},
  volume={28},
  pages={3637--3665},
  doi={10.1109/COMST.2025.3622378}
}