This paper focuses on the anti-jamming transmission problem in unmanned aerial vehicle (UAV) communication networks. Considering the incomplete information constraint and the co-channel mutual interference, a Bayesian Stackelberg game is proposed to formulate the competitive relations between UAVs (users) and the jammer. Specifically, the jammer acts as the leader, whereas users act as followers of the proposed game. Based on their utility functions, the jammer and users select their optimal power control strategies respectively. In addition, the observation error is also investigated in this paper. Due to the incomplete information constraint and the existence of co-channel mutual interference, it is challenging to obtain Stackelberg equilibrium (SE) of the proposed game. Thus, a sub-gradient based Bayesian Stackelberg iterative algorithm is proposed to obtain SE. Finally, simulations are conducted to demonstrate the performance of the proposed algorithm, and the impact of incomplete information and observation error on users' utilities are also presented.

This paper investigates the problem of anti-jamming communication in dynamic and intelligent jamming environment. A sequential deep reinforcement learning algorithm (SDRLA) without prior information is proposed, and raw spectrum information is used as the input of SDRLA. The proposed SDRLA algorithm mainly contains two parts: Firstly, deep learning and sliding window principle are introduced to identify jamming patterns; Secondly, reinforcement learning is carried out to make on-line channel selection based on recognized jamming patterns. In addition, channel switching cost is introduced for the purpose of formulating the trade-off relationship between throughput and overhead. Taking advantage of both deep learning and reinforcement learning, this method can realize rapid and effective anti-jamming channel selection with no need for modeling the jammer's characteristics. Simulation results show the convergence and effectiveness of the proposed SDRLA algorithm. Compared with single-mode reinforcement learning, our approach can reach better convergence performance and higher utility.

Intelligent reflective surfaces (IRSs) as low energy consumption and easy to attach devices have been widely applied in the field of anti-jamming recently. In particular, the combination of IRS and unmanned aerial vehicle (UAV), as IRS-UAV, further expands the scope of IRS services. In this article, the joint IRS selection and beamforming optimization problem has been investigated in multiple IRS-UAV-assisted anti-jamming D2D networks. To solve the above optimization problem, a distributed matching-based selection and $Q$ -learning-based beamforming optimization algorithm (DMQ) was proposed. In detail, the optimization problem is decomposed into two subproblems, namely, the IRS selection subproblem is formulated as a noncommutative many-to-many matching game model to describe peer effects and uncertainty selection quotas, and the passive beamforming optimization subproblem is solved by a reinforcement algorithm to satisfy the complex environment. Numerical simulations confirm the convergence and near-optimal performance of the proposed scheme with lower latency and greater robustness.

This paper mainly investigates the multi-user anti-jamming spectrum access problem. Using the idea of "converting harm into benefit", the malicious jamming signals projected by the enemy are utilized by the users as the coordination signals to guide spectrum coordination. An "internal coordination-external confrontation" multi-user anti-jamming access game model is constructed, and the existence of Nash equilibrium (NE) as well as correlated equilibrium (CE) is demonstrated. A coordination-learning based anti-jamming spectrum access algorithm (CLASA) is designed to achieve the CE of the game. Simulation results show the convergence and effectiveness of the proposed CLASA algorithm, and indicate that our approach can help users confront the malicious jammer and coordinate internal spectrum access simultaneously without information exchange. Last but not least, the fairness of the proposed approach under different jamming attack patterns is analyzed, which illustrates that this approach provides fair anti-jamming spectrum access opportunities under complicated jamming pattern.

This letter studies the problem of anti-jamming spectrum access in dynamic and unknown environments with incomplete spectrum sensing information. Most existing studies were based on the assumption that users have perfect spectrum information, thus they worked poorly with incomplete sensing information. To overcome the shortcoming, we present a robust intelligent anti-jamming spectrum access scheme which includes spectrum sensing, completion, learning and access. To complete the missing spectrum data, we design a generative adversarial network (GAN) based spectrum completion network. Based on deep reinforcement learning (DRL), a channel selection network is introduced to choose effective anti-jamming channel access policy. Simulation results show that the proposed approach is able to avoid complex jamming attacks effectively and outperforms conventional DRL-based approach with incomplete spectrum information.

This letter studies the problem of deep reinforcement learning (DRL)-based dynamic spectrum anti-jamming access in overlay cognitive radio networks. To prevent secondary user (SU) from interfering with primary user (PU) and being jammed by jammer, we propose a PU-friendly dynamic spectrum anti-jamming access scheme. First, a generative adversarial network (GAN)-based virtual environment is proposed to simulate spectrum environment. Then, a DRL-based channel decision network (CDN) is trained to learn the optimal spectrum access policy in the virtual environment. Finally, SU accesses spectrum environment under the guidance of the trained CDN. Simulation results show that the proposed scheme is able to elude both PU signals and jamming completely and converges much faster than the scheme that trains the CDN in spectrum environment from scratch.