Jamming Strategy Generation for Hidden Communication Modes Via Graph Convolution Networks

Optimal jamming has important applications in both military and civil communications. There have been a brunch of works investigating the optimal jamming signal design when the signal modes of the opponent are known. In this work, we focus on the less studied hidden mode jamming problem. That is, the jammer has partially recorded the signal modes of the opponent, but there are some hidden modes not revealed to the jammer as of the appearance of these modes. As such, when the hidden modes appear, the jammer has to quickly adapt its jamming strategy to achieve effective jamming. However, it is challenging to do so due to incomplete knowledge of the intrinsic relation between the known and the hidden modes. In this work, a learning-based approach is proposed to attack this problem. Specifically, we custom-devise a jamming network (J-Net) to automatically learn the intrinsic relation among different modes and transfer the jamming strategy from the known modes to the hidden ones. Experimental results demonstrate that the J-Net attains much better jamming effect than pulsed Gaussian jamming and random jamming, and is comparable to the reinforcement learning-based approach, which assumes all the (known and hidden) modes available at the jammer.