G gaps are identified in adversarial over-the-air (OTA) validation, cross-layer threat modeling, reproducible Radio-Frequency datasets, and lifecycle evidence for body-centric and time-critical cyber-physical systems.
Abstract
Sixth-generation (6G) wireless networks are evolving toward Artificial Intelligence (AI)-native architectures in which learning-based functions enter physical-layer processing, radio access, edge platforms, and network control. These functions can improve adaptation and spectrum use, but training data, model updates, telemetry, and control interfaces also create attack surfaces. In safety-critical environments, failures may cause not only communication disruption but physical harm, operational instability, or regulatory non-compliance. This survey considers Physical Layer Security (PLS) in its broad sense, encompassing confidentiality, authentication, availability and resilience, and sensing or location privacy. Within this scope, we examine three relationships between AI and PLS: AI used to strengthen PLS mechanisms, AI used to undermine their assumptions or defenses, and the security of learning components embedded in PLS control loops. The literature is organized by security objective, attacker capability, lifecycle stage, and experimental evidence. The selected evidence illustrates that mechanism-level improvements alone are insufficient to establish end-to-end security. Exposed models and telemetry, programmable propagation, distribution shift, and closed-loop timing introduce assurance requirements not captured by secrecy rate or classifier accuracy alone. We therefore identify gaps in adversarial over-the-air (OTA) validation, cross-layer threat modeling, reproducible Radio-Frequency (RF) datasets, and lifecycle evidence for body-centric and time-critical cyber-physical systems. Addressing these gaps requires evaluations that connect physical assumptions and learned decisions to operational consequences and recovery behavior.
Sixth-generation (6G) networks are expected to integrate artificial intelligence (AI) into distributed and highly adaptive communication infrastructures. This convergence creates opportunities for intelligent routing, but also exposes routing decisions, learning models and trust relationships to complex security threat...
Mohd Hilal Muhammad, Muhammad Khairul Zharif Nor A'Zam, Mohd Zhafri Mohd Zukhi· International journal of res...· 0 citations
Integrated sensing and communication (ISAC) has emerged as a key enabler for sixth-generation (6G) networks, yet its broadcast nature at the physical layer leaves transmissions vulnerable to malicious eavesdropping, particularly when physical blockages degrade direct links. Reconfigurable intelligent surface (RIS) offe...
Zhen-Dong Li, Jin-Yuan Huang, Wei-Chun Zhao et al.· 1 citation
Evidence from recent surveys, standards and industry reports indicates that AI can shorten detection and response times and reduce breach costs, but only when it is governed carefully and protected as a target in its own right.
Rajalakshmanan· International Journal for Re...· 0 citations
Optical networks carry most of today's high-capacity digital traffic, yet their physical and photonic layers remain difficult to secure with conventional tools such as firewalls or generic encryption. This paper reviews 21 studies published between 2018 and 2025 on cybersecurity in optical networks, examining threats a...
Reyhaneh Ahmadpour, Mehmet Yavuz Yağcı, Muhammed Ali Aydin· 2026 11th International Conf...· 0 citations
Special focus is placed on the CIA+Auth model (confidentiality, integrity, availability, and authentication) as the basis for designing secure systems and the ABAC model provides greater flexibility and suitability for Li-Fi environments due to the ability to include contextual factors such as location, time, and risk...
Ljubinko Stojanović, P. Spalevic· ZBORNIK RADOVA UNIVERZITETA...· 0 citations
By combining the Zero Trust model with Li-Fi communication and secure key management mechanisms, a layered approach is provided for securing sensitive internal wireless communication against eavesdropping, message manipulation, and unauthorized access.