Incorporating both semantic level information and effectiveness level performance, the task-oriented semantic communication system has been designed for various tasks of different datatype. Although semantic communication improves the spectral utilization to some extent, indiscriminate transmission of semantic information for task-oriented semantic communication can still result in waste of wireless resources. In this paper, we propose an importance-aware joint source-channel coding (I-JSCC) framework for task-oriented semantic communications. A joint semantic-channel transmission (JSCT) mechanism is designed by selectively transmitting task-important features to reduce communication overhead. We define a new metric named task-oriented semantic spectral efficiency (TOSSE) to evaluate the effectiveness and efficiency of the proposed system, which measures the effective semantic information carried by each semantic symbol. An importance-aware semantic resource allocation problem is formulated to maximize the total TOSSE of all users by jointly optimizing the channel assignment and feature selection vector. To solve this problem, a knowledge-assisted proximal policy optimization (K-PPO) based reinforcement learning (RL) algorithm is proposed. The experimental results conducted on CIFAR100 dataset demonstrate the efficacy of the K-PPO algorithm, while also highlighting the superiority of the importance-aware semantic communication system in terms of the TOSSE.

Recently, physical-layer authentication (PLA) has attracted much attention since it takes advantage of the channel randomness nature of transmission media to achieve communication confidentiality and authentication. In the complex environment, such as the Industrial Internet of Things (IIoT), machine learning (ML) is widely employed with PLA to extract and analyze complex channel characteristics for identity authentication. However, most PLA schemes for IIoT require attackers’ prior channel information, leading to severe performance degradation when the source of the received signals is unknown in the training stage. Thus, a channel impulse response (CIR)-based PLA scheme named “hierarchical variational autoencoder (HVAE)” for IIoT is proposed in this article, aiming at achieving high authentication performance without knowing attackers’ prior channel information even when trained on a few data in the complex environment. HVAE consists of an autoencoder (AE) module for CIR characteristics extraction and a variational AE (VAE) module for improving the representation ability of the CIR characteristic and outputting the authentication results. Besides, a new objective function is constructed in which both the single-peak and the double-peak Gaussian distributions are taken into consideration in the VAE module. Moreover, the simulations are conducted under the static and mobile IIoT scenario, which verify the superiority of the proposed HVAE over three comparison PLA schemes even with a few training data.

With the rapid advancement of 6G, identity authentication has become increasingly critical for ensuring wireless security. The lightweight and keyless Physical Layer Authentication (PLA) is regarded as an instrumental security measure in addition to traditional cryptography-based authentication methods. However, existing PLA schemes often struggle to adapt to dynamic radio environments. To overcome this limitation, we propose the Adaptive PLA with Channel Extrapolation and Generative AI (APEG), designed to enhance authentication robustness in dynamic scenarios. Leveraging Generative AI (GAI), the framework adaptively generates Channel State Information (CSI) fingerprints, thereby improving the precision of identity verification. To refine CSI fingerprint generation, we propose the Collaborator-Cleaned Masked Denoising Diffusion Probabilistic Model (CCMDM), which incorporates collaborator-provided fingerprints as conditional inputs for channel extrapolation. Additionally, we develop the Cross-Attention Denoising Diffusion Probabilistic Model (CADM), employing a cross-attention mechanism to align multi-scale channel fingerprint features, further enhancing generation accuracy. Simulation results demonstrate the superiority of the APEG framework over existing time-sequence-based PLA schemes in authentication performance. Notably, CCMDM exhibits a significant advantage in convergence speed, while CADM, compared with model-free, time-series, and VAE-based methods, achieves superior accuracy in CSI fingerprint generation. The code is available at https://github.com/xiqicheng192-del/APEG

We propose a novel task-oriented and semantic-aware heterogeneous networks (TOSA-HetNets) framework for multi-type Artificial Intelligence of Things (AIoT) devices with various requirements, where the dense edge servers with different transmission capabilities, computing resources, and power consumption are divided into different layers to provide on-demand collaboration for AIoT devices located in accessible areas. Moreover, we propose a device-edge collaboration intelligent tasks inference scheme between edge servers and AIoT devices in TOSA-HetNets, it includes AIoT devices performing semantic features extraction and uploading the corresponding semantic features to the associated edge servers, multiple layers of edge servers collaborating with AIoT devices to execute the intelligent tasks and transmit the intelligent task results back to AIoT devices. To investigate the performance of TOSA-HetNets in supporting device-edge collaboration intelligent tasks inference, we adopt stochastic geometry to obtain the closed-form expressions of average task success probability, power consumption, and network throughput in the downlink transmission. Furthermore, we define a metric of average achievable task back-transmission energy efficiency (TBT-EE) to measure the information bit of successfully transmitted correct intelligent task results with unit power consumption, which is a function of average task success probability, average network throughput on the unit area, and the total power consumption. Meanwhile, we maximize the average achievable TBT-EE by optimizing the density of edge servers and the average semantic compression ratio. Simulation results verify the correctness of the obtained closed-form expressions and show that the edge servers’ density and average semantic compression ratio have different influences on the performance of TOSA-HetNets.