SemantiGuard: AI-Driven Cyber Threat Intelligence for 6G Semantic Communications

Evram Magdy Mikhail; Syed T. Shah; Hassan Malik; Walid M. Saad; Mahmoud A. Shawky

SemantiGuard: AI-Driven Cyber Threat Intelligence for 6G Semantic Communications

Evram Magdy Mikhail
, Syed T. Shah
, Hassan Malik
, Walid M. Saad
, Mahmoud A. Shawky

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

As 6G networks shift from bit-oriented communication toward Semantic Communication (SemCom), the physical layer becomes vulnerable to a new type of threat called Semantic Adversarial Attacks. In these attacks, adversaries
generate precise, low-energy perturbations to alter the meaning of
transmitted data while evading detection by traditional energy based security systems. This paper presents SemantiGuard, a cyber threat intelligence (CTI) framework that uses deep joint source-channel coding (Deep JSCC) with unsupervised geometric anomaly detection mechanism to secure the SemCom systems by monitoring the high-dimensional latent manifold, our framework
is able to detect the legitimate signals as well as the malicious gradient-optimized perturbations. Using a developed simulation environment, we demonstrate that SemantiGuard achieves more than 84% detection accuracy even in high noise radio environments. Our findings highlights the importance of spatial-aware security layers to ensure the integrity of the critical control
messages in the future of autonomous and energy sustainable 6G network architectures.

Original language	English
Title of host publication	IEEE Vehicular Technology Conference (Fall) 2026
Publication status	Accepted/In press - 21 Jun 2026

Access to Document

VTS_Conference_2026__Revised_Final_Jun26Accepted author manuscript, 3.74 MBLicence: CC BY

Cite this

@inproceedings{3e7c6208c09f4cbf8702907a40f4f574,

title = "SemantiGuard: AI-Driven Cyber Threat Intelligence for 6G Semantic Communications",

abstract = "As 6G networks shift from bit-oriented communication toward Semantic Communication (SemCom), the physical layer becomes vulnerable to a new type of threat called Semantic Adversarial Attacks. In these attacks, adversaries generate precise, low-energy perturbations to alter the meaning of transmitted data while evading detection by traditional energy based security systems. This paper presents SemantiGuard, a cyber threat intelligence (CTI) framework that uses deep joint source-channel coding (Deep JSCC) with unsupervised geometric anomaly detection mechanism to secure the SemCom systems by monitoring the high-dimensional latent manifold, our framework is able to detect the legitimate signals as well as the malicious gradient-optimized perturbations. Using a developed simulation environment, we demonstrate that SemantiGuard achieves more than 84\% detection accuracy even in high noise radio environments. Our findings highlights the importance of spatial-aware security layers to ensure the integrity of the critical control messages in the future of autonomous and energy sustainable 6G network architectures.",

author = "Mikhail, \{Evram Magdy\} and Shah, \{Syed T.\} and Hassan Malik and Saad, \{Walid M.\} and Shawky, \{Mahmoud A.\}",

year = "2026",

month = jun,

day = "21",

language = "English",

booktitle = "IEEE Vehicular Technology Conference (Fall) 2026",

}

TY - GEN

T1 - SemantiGuard: AI-Driven Cyber Threat Intelligence for 6G Semantic Communications

AU - Mikhail, Evram Magdy

AU - Shah, Syed T.

AU - Malik, Hassan

AU - Saad, Walid M.

AU - Shawky, Mahmoud A.

PY - 2026/6/21

Y1 - 2026/6/21

N2 - As 6G networks shift from bit-oriented communication toward Semantic Communication (SemCom), the physical layer becomes vulnerable to a new type of threat called Semantic Adversarial Attacks. In these attacks, adversaries generate precise, low-energy perturbations to alter the meaning of transmitted data while evading detection by traditional energy based security systems. This paper presents SemantiGuard, a cyber threat intelligence (CTI) framework that uses deep joint source-channel coding (Deep JSCC) with unsupervised geometric anomaly detection mechanism to secure the SemCom systems by monitoring the high-dimensional latent manifold, our framework is able to detect the legitimate signals as well as the malicious gradient-optimized perturbations. Using a developed simulation environment, we demonstrate that SemantiGuard achieves more than 84% detection accuracy even in high noise radio environments. Our findings highlights the importance of spatial-aware security layers to ensure the integrity of the critical control messages in the future of autonomous and energy sustainable 6G network architectures.

AB - As 6G networks shift from bit-oriented communication toward Semantic Communication (SemCom), the physical layer becomes vulnerable to a new type of threat called Semantic Adversarial Attacks. In these attacks, adversaries generate precise, low-energy perturbations to alter the meaning of transmitted data while evading detection by traditional energy based security systems. This paper presents SemantiGuard, a cyber threat intelligence (CTI) framework that uses deep joint source-channel coding (Deep JSCC) with unsupervised geometric anomaly detection mechanism to secure the SemCom systems by monitoring the high-dimensional latent manifold, our framework is able to detect the legitimate signals as well as the malicious gradient-optimized perturbations. Using a developed simulation environment, we demonstrate that SemantiGuard achieves more than 84% detection accuracy even in high noise radio environments. Our findings highlights the importance of spatial-aware security layers to ensure the integrity of the critical control messages in the future of autonomous and energy sustainable 6G network architectures.

M3 - Conference contribution

BT - IEEE Vehicular Technology Conference (Fall) 2026

ER -