SemProtector: A Unified Framework for Semantic Protection in Deep Learning-based Semantic Communication Systems
Xinghan Liu, Guoshun Nan, Qimei Cui, Zeju Li, Peiyuan Liu, Zebin Xing, Hanqing Mu, Xiaofeng Tao, Tony Q. S. Quek
Abstract
Recently proliferated semantic communications (SC) aim at effectively transmitting semantics conveyed by a source, and accurately interpreting the meaning at its destination. While such a paradigm holds the promise of making wireless communications more intelligent, it also suffers from severe semantic security issues - such as eavesdropping, privacy leaking, and spoofing - due to the open nature of wireless channels and the fragility of neural modules. Previous works focus more on the robustness of SC via offline adversarial training of a whole system, while online semantic protection - a more practical setting in the real world - is still largely under-explored. To this end, we present SemProtector, a unified framework that aims to secure an online SC system with three hot-pluggable semantic protection modules. Specifically, these modules are able to encrypt semantics to be transmitted by an encryption method, mitigate privacy risks from wireless channels by a perturbation mechanism, and calibrate distorted semantics at the destination by a semantic signature generation method. Our framework enables an existing online SC system to dynamically assemble the above three pluggable modules to meet customized semantic protection requirements, facilitating the practical deployment in real-world SC systems. Experiments on two public datasets show the effectiveness of our proposed SemProtector, offering some insights of how we reach the goal of secrecy, privacy, and integrity of an SC system. Finally, we discuss a few future directions for semantic protection.