Toward Mixture-of-Experts Enabled Trustworthy Semantic Communication for 6G Networks
This addresses security challenges for practical semantic communication applications in 6G networks, such as vehicular networks, and is incremental as it builds on existing defenses to handle multiple attacks simultaneously.
The paper tackles the vulnerability of deep learning-based semantic communication systems in 6G networks to multiple heterogeneous security threats like adversarial attacks, and introduces a Mixture-of-Experts-based system that effectively mitigates these attacks with minimal impact on task accuracy.
Semantic Communication (SemCom) plays a pivotal role in 6G networks, offering a viable solution for future efficient communication. Deep Learning (DL)-based semantic codecs further enhance this 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 enable 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 introduce a novel Mixture-of-Experts (MoE)-based SemCom system. This system comprises 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.