Large language models have demonstrated the ability to performin-context learning(ICL), whereby the model performs predictions by directly mapping the query and a few examples from the given task to the output variable. In this paper, we study ICL for deep joint source-channel coding (DeepJSCC) in image transmission over multiple-input multiple-output (MIMO) systems, where an ICL denoiser is employed for MIMO symbol estimation. We first study the transceiver without any hardware impairments and explore the integration of transformer-based ICL with DeepJSCC in both open-loop and closed-loop MIMO systems, depending on the availability of channel state information (CSI) at the transceiver. For both open-loop and closed-loop scenarios, we propose two MIMO transceiver architectures that leverage context information, i.e., pilot sequences and their outputs, as additional inputs, enabling the DeepJSCC encoder, DeepJSCC decoder, and the ICL denoiser to jointly learn encoding, decoding, and estimation strategies tailored to each channel realization. Next, we extend our study to a more challenging scenario where the transceiver suffers from in-phase and quadrature (IQ) imbalance, resulting in nonlinear MIMO estimation. In this case, the context information is also exploited, facilitating joint learning across the DeepJSCC encoder, decoder, and the ICL denoiser under hardware impairments and varying channel conditions. Numerical results demonstrate that the ICL denoiser for MIMO estimation significantly outperforms the conventional least-squares method, with even greater advantages under IQ imbalance. Moreover, the proposed transformer-based ICL framework, integrated with contextual information, achieves significant improvements in end-to-end image reconstruction quality under transceiver IQ imbalance.

In this paper, a novel covert semantic communication framework is investigated. Within this framework, a server extracts and transmits the semantic information, i.e., the meaning of image data, to a user over several time slots. An attacker seeks to detect and eavesdrop the semantic transmission to acquire details of the original image. To avoid data meaning being eavesdropped by an attacker, a friendly jammer is deployed to transmit jamming signals to interfere the attacker so as to hide the transmitted semantic information. Meanwhile, the server will strategically select time slots for semantic information transmission. Due to limited energy, the jammer will not communicate with the server and hence the server does not know the transmit power of the jammer. Therefore, the server must jointly optimize the semantic information transmitted at each time slot and the corresponding transmit power to maximize the privacy and the semantic information transmission quality of the user. To solve this problem, we propose a prioritised sampling assisted twin delayed deep deterministic policy gradient algorithm to jointly determine the transmitted semantic information and the transmit power per time slot without the communications between the server and the jammer. Compared to standard reinforcement learning methods, the proposed method uses an additional Q network to estimate Q values such that the agent can select the action with a lower Q value from the two Q networks thus avoiding local optimal action selection and estimation bias of Q values. Simulation results show that the proposed algorithm can improve the privacy and the semantic information transmission quality by up to 77.8% and 14.3% compared to the traditional reinforcement learning methods.

In this paper, a novel covert semantic communication framework is investigated for image transmission. Within this framework, a server extracts and transmits the semantic information, i.e., the meaning of image data, to a user. An attacker seeks to detect and eavesdrop the semantic transmission to acquire the details of the original image. To secure the semantic communications from such eavesdropping attack, a friendly jammer is deployed to transmit jamming signals so as to interfere the attacker. To evaluate the quality of the received and the eavesdropped semantic information, we introduce a semantic similarity metric called graph-to-nearest-triple (GNT). The privacy level of the system is quantified as the difference between the GNT of the received semantic information at the user and the attacker. The server and the jammer collaboratively manage their transmit power to maximize the privacy level of the semantic communication. To solve this non-convex power management problem, we propose a step-wise dense reward function guided recurrent Q learning algorithm to jointly optimize the transmit power at the server and friendly jammer with no inter-device communication, such that the considered problem is solved in a spectrally, computationally and space compact way. Simulation results show that the proposed method can improve privacy and the semantic transmission quality by up to 17.2% improvement compared to the traditional RL based solutions.

In this paper, a semantic communication framework for image data transmission is developed. In the investigated framework, a set of servers cooperatively transmit image data to a set of users utilizing semantic communication techniques, which enable servers to transmit only the semantic information that accurately captures the meaning of images. To evaluate the performance of studied semantic communication system, a multimodal metric called image-to-graph semantic similarity (ISS) is proposed to measure the correlation between the extracted semantic information and the original image. To meet the ISS requirement of each user, each server must jointly determine the semantic information to be transmitted and the resource blocks (RBs) used for semantic information transmission. Due to the co-channel interference among users associated with different servers, each server must cooperate with other servers to find a globally optimal semantic oriented RB allocation. We formulate this problem as an optimization problem whose goal is to minimize the sum of the average transmission latency of each server while reaching the ISS requirement. To solve this problem, we propose a value decomposition based entropy-maximized multi-agent reinforcement learning (RL) algorithm. The proposed algorithm enables each server to coordinate with other servers in training stage and execute RB allocation in a distributed manner to approach to a globally optimal performance with less training iterations. Compared to traditional multi-agent RL algorithms, the proposed RL framework improves the exploration of valuable action of servers and the probability of finding a globally optimal RB allocation policy based on local observation of wireless and semantic communication environments. Simulation results show that the proposed algorithm can reduce the transmission delay by up to 16.1% and improve the convergence speed by up to 100% compared to the traditional multi-agent RL algorithms.

In this paper, a semantic communication framework for image transmission is investigated. In the framework, a server transmits image data to a set of users utilizing semantic communication techniques, which enable the server to transmit only the semantic information that accurately captures the meaning of an image. To evaluate the performance of the studied semantic communication system, we propose a multimodal metric called image-to-graph semantic similarity (ISS). The significance of this new metric is that it can measure the correlation of the meaning between semantic information and the original image. To meet the ISS requirement of each user, the server must jointly determine the semantic information to be transmitted and the resource blocks (RBs) used for semantic information transmission. We formulate this problem as an optimization problem whose goal is to minimize the average transmission latency while reaching the ISS requirement. To solve this problem, we propose a model-based actor critic deep reinforcement learning (DRL) algorithm. Compared to traditional actor critic DRL, in the proposed algorithm, we design a novel value function to improve the action exploration thus improving the probability of finding an optimal solution. Simulation results show that the proposed method can reduce the transmission delay by 16.4% and improves the convergence speed by up to 50% compared to the traditional actor critic DRL.