Adaptive Learning for IRS-Assisted Wireless Networks: Securing Opportunistic Communications Against Byzantine Eavesdroppers

We propose a joint learning framework for Byzantine-resilient spectrum sensing and secure intelligent reflecting surface (IRS)--assisted opportunistic access under channel state information (CSI) uncertainty. The sensing stage performs logit-domain Bayesian updates with trimmed aggregation and attention-weighted consensus, and the base station (BS) fuses network beliefs with a conservative minimum rule, preserving detection accuracy under a bounded number of Byzantine users. Conditioned on the sensing outcome, we pose downlink design as sum mean-squared error (MSE) minimization under transmit-power and signal-leakage constraints and jointly optimize the BS precoder, IRS phase shifts, and user equalizers. With partial (or known) CSI, we develop an augmented-Lagrangian alternating algorithm with projected updates and provide provable sublinear convergence, with accelerated rates under mild local curvature. With unknown CSI, we perform constrained Bayesian optimization (BO) in a geometry-aware low-dimensional latent space using Gaussian process (GP) surrogates; we prove regret bounds for a constrained upper confidence bound (UCB) variant of the BO module, and demonstrate strong empirical performance of the implemented procedure. Simulations across diverse network conditions show higher detection probability at fixed false-alarm rate under adversarial attacks, large reductions in sum MSE for honest users, strong suppression of eavesdropper signal power, and fast convergence. The framework offers a practical path to secure opportunistic communication that adapts to CSI availability while coherently coordinating sensing and transmission through joint learning.

Large Array Antenna Spectrum Sensing in Cognitive Radio Networks

We investigate the problem of spectrum sensing in cognitive radios (CRs) when the receivers are equipped with a large array of antennas. We propose and derive three detectors based on the concept of linear spectral statistics (LSS) in the field of random matrix theory (RMT). These detectors correspond to the generalized likelihood ratio (GLR), Frobenius norm, and Rao tests employed in conventional multiple antenna spectrum sensing (MASS). Subsequently, we compute the Gaussian distribution of the proposed detectors under the noise-only hypothesis, leveraging the central limit theorem (CLT) applied to high-dimensional random matrices. We evaluate the performance of the proposed detectors and analyze the impact of the number of antennas and samples on their efficacy. Furthermore, we assess the accuracy of the theoretical results by comparing them with simulation outcomes. The simulation results provide evidence that the proposed detectors exhibit efficient performance in wireless networks featuring large array antennas. These detectors find practical applications in diverse domains, including massive MIMO wireless communications, radar systems, and astronomical applications.