Toward Mixture-of-Experts Enabled Trustworthy Semantic Communication for 6G Networks
IEEE Network · 2025-09 · 39 (5) · 221-230
DOI: 10.1109/mnet.2024.3523181 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Network, 2025-09. Verfasst von Jiayi He und 7 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 15 Literaturangaben.
Abstract (Originalsprache)
Semantic Communication (SemCom) plays a pivotal role in 6G networks, offering a viable solution for future efficient communication. Through nonlinear mapping of semantic representations, Deep Learning (DL)-based semantic communications further enhance communication efficiency. However, the vulnerability of DL models to security threats, such as adversarial attacks, poses significant challenges for practical applications of SemCom systems. These vulnerabilities allow attackers to tamper with messages and eavesdrop on private information, especially in wireless communication scenarios. Although existing defenses attempt to address specific threats, they often fail to simultaneously handle multiple heterogeneous attacks. To overcome this limitation, we propose a novel Mixture-of-Experts (MoE)-based SemCom system, comprising a gating network and multiple experts, each specializing in different security challenges. The gating network adaptively selects suitable experts to counter heterogeneous attacks based on user-defined security requirements. Multiple experts collaborate to accomplish semantic communication tasks while meeting the security requirements of users. A case study in vehicular networks demonstrates the efficacy of the MoE-based SemCom system. Simulation results show that the proposed MoE-based SemCom system effectively mitigates concurrent heterogeneous attacks, with minimal impact on downstream task accuracy.
Zitieren
APA
He, J., Luo, X., Kang, J., Du, H., Xiong, Z., Chen, C., Niyato, D., & Shen, X. (2025). Toward Mixture-of-Experts Enabled Trustworthy Semantic Communication for 6G Networks. IEEE Network, 39(5), 221-230. https://doi.org/10.1109/mnet.2024.3523181
Vancouver
He J, Luo X, Kang J, Du H, Xiong Z, Chen C, et al. Toward Mixture-of-Experts Enabled Trustworthy Semantic Communication for 6G Networks. IEEE Network. 2025;39(5):221-230. doi:10.1109/mnet.2024.3523181
BibTeX
@article{He2025,
author = {He, Jiayi and Luo, Xiaofeng and Kang, Jiawen and Du, Hongyang and Xiong, Zehui and Chen, Ci and Niyato, Dusit and Shen, Xuemin},
title = {Toward Mixture-of-Experts Enabled Trustworthy Semantic Communication for 6G Networks},
journal = {IEEE Network},
year = {2025},
volume = {39},
number = {5},
pages = {221--230},
doi = {10.1109/mnet.2024.3523181}
}
EUVIMED