Adversarial, yet Friendly Signal Design for Secured Wireless Communication

Whenever wireless communication link becomes a unique communication means, ensuring security is just as important as achieving fast and reliable communication especially for military and medical systems. A common approach for secure wireless communication is via encryption of the information but this may fail to provide complete security (e.g., vulnerable to side-channel attack) especially when it comes with computation-limited scenarios such as Internet of Things (IoT) case. A simpler, yet powerful alternative technique to improve security is by preventing eavesdroppers from knowing correct modulation and coding (MCS) scheme. In traditional wireless communication systems, this MCS information can be secured based on sophisticate design of mutually cooperative strategies between the transmitter and the receiver. However, for deep learning (DL)-based wireless communication systems, this cooperation can be significantly simplified by just adding a well-designed adversarial signal to the transmitted signal. In this paper, we propose a novel, transferable adversarial signal design that simultaneously prevents non-cooperative eavesdroppers from achieving correct modulation scheme while ensuring the intended, cooperative receiver’s correct acquisition of the modulation scheme. Extensive numerical results validate secrecy of the proposed scheme along with transferability.