This paper investigates covert prompt transmission for secure and efficient large language model (LLM) services over wireless networks. We formulate a latency minimization problem under fidelity and detectability constraints to ensure confidential and covert communication by jointly optimizing the transmit power and prompt compression ratio. To solve this problem, we first propose a prompt compression and encryption (PCAE) framework, performing surprisal-guided compression followed by lightweight permutation-based encryption. Specifically, PCAE employs a locally deployed small language model (SLM) to estimate token-level surprisal scores, selectively retaining semantically critical tokens while discarding redundant ones. This significantly reduces computational overhead and transmission duration. To further enhance covert wireless transmission, we then develop a group-based proximal policy optimization (GPPO) method that samples multiple candidate actions for each state, selecting the optimal one within each group and incorporating a Kullback-Leibler (KL) divergence penalty to improve policy stability and exploration. Simulation results show that PCAE achieves comparable LLM response fidelity to baseline methods while reducing preprocessing latency by over five orders of magnitude, enabling real-time edge deployment. We further validate PCAE effectiveness across diverse LLM backbones, including DeepSeek-32B, Qwen-32B, and their smaller variants. Moreover, GPPO reduces covert transmission latency by up to 38.6% compared to existing reinforcement learning strategies, with further analysis showing that increased transmit power provides additional latency benefits.

Semantic communication (SemCom) has recently emerged as a promising approach to enhance communication efficiency by transmitting only important semantic information. In eavesdropping environments, the semantic information may be overheard by the eavesdropper even under poor channel conditions with a powerful semantic decoder. Some advanced secure communication deployments such as autoencoder-enhanced Sem-Com (AE-SemCom) and generative model-enhanced SemCom (GEN-SemCom) have been introduced to efficiently transmit the semantic information. However, these secure solutions require retraining the semantic encoder and decoder, which limits the flexibility and practical deployment. To address this issue, we propose a secure SemCom framework for AE-SemCom and GEN-SemCom without altering the parameters of the semantic encoder and decoder. Specifically, we propose to deploy a cooperative jammer to transmit optimized jamming signal to deteriorate the decoding ability of eavesdropper, while a residual refinement module (RRM) is used at the legitimate receiver to mitigate the impact of these jamming signal. Moreover, to achieve an efficient trade-off between transmission security and reliability, we then introduce a cooperative training strategy by formulating this optimization problem as a two-player game between the jammer and Bob. Finally, we conduct extensive simulations to evaluate the effectiveness of the proposed framework across face recognition dataset. In particular, with a jamming power of 0.3, the eavesdropper experiences up to a 12dB reduction in the peak signal-to-noise ratio (PSNR) of reconstructed images compared to the baselines without the proposed security framework while maintaining high-quality image reconstruction for legitimate users.

Semantic communication (SemCom) has recently emerged as a promising paradigm for next-generation wireless systems. Empowered by advanced artificial intelligence (AI) technologies, SemCom has achieved significant improvements in transmission quality and efficiency. However, existing SemCom systems either rely on training over large datasets and specific channel conditions or suffer from performance degradation under channel noise when operating in a training-free manner. To address these issues, we explore the use of generative diffusion models (GDMs) as training-free SemCom systems. Specifically, we design a semantic encoding and decoding method based on the inversion and sampling process of the denoising diffusion implicit model (DDIM), which introduces a two-stage forward diffusion process, split between the transmitter and receiver to enhance robustness against channel noise. Moreover, we optimize sampling steps to compensate for the increased noise level caused by channel noise. We also conduct a brief analysis to provide insights about this design. Simulations on the Kodak dataset validate that the proposed system outperforms the existing baseline SemCom systems across various metrics.

Semantic communication (SemCom) has emerged as a key technology for the forthcoming sixth-generation (6G) network, attributed to its enhanced communication efficiency and robustness against channel noise. However, the open nature of wireless channels makes them vulnerable to eavesdropping, which poses a serious threat to privacy. To address this issue, we propose a novel secure semantic communication (SemCom) approach for image transmission, which integrates steganography technology to conceal private information within non-private images (host images). Specifically, we propose an invertible neural network (INN)-based signal steganography approach that embeds channel input signals of a private image into those of a host image before transmission. This ensures that the original private image can be reconstructed from the received signals at the legitimate receiver, while the eavesdropper can only decode the information of the host image. Simulation results demonstrate that the proposed approach maintains comparable reconstruction quality of both host and private images at the legitimate receiver, compared to scenarios without any secure mechanisms. Moreover, the results indicate that the eavesdropper is only able to reconstruct host images, showcasing the enhanced security provided by our approach.

Learning-based semantic communication (SemCom) has emerged as a promising solution for the upcoming 6G networks. In this paper, we explore an evolving SemCom system for image transmission, which can continuously adapt and enhance its transmission efficiency by exploiting knowledge accumulated during previous transmissions. Specifically, we propose a novel channel-aware semantic encoder that utilizes a pretrained generative model to extract channel-correlated latent variables consisting of several semantic vectors from the input images, which can be directly transmitted over a noisy channel without further channel coding. Moreover, we introduce a dynamic code construction mechanism that dynamically updates the codebook with transmitted semantic vectors to eliminate the need to transmit similar codes in subsequent transmissions, thus further reducing the communication overhead. Simulation results highlight the evolving performance of the proposed system in terms of transmission efficiency, achieving superior perceptual quality with an average bandwidth compression ratio (BCR) of $1 / 192$ for a sequence of 100 test images compared to DeepJSCC and InverseJSCC. Code used in this paper is available at https://github.com/recusant7/GAN_SeCom.

Recently, there has been a growing interest in learning-based semantic communication because it can prioritize the preservation of meaningful semantic information over the accuracy of the transmitted symbols, resulting in improved communication efficiency. However, existing learning-based approaches still face limitations in defining semantic level loss and often struggle to find a good trade-off between preserving semantic information and preserving intricate details. In addition, the existing semantic communication approaches cannot effectively train semantic encoders and decoders without the support of downstream models. To address these limitations, this paper proposes a contrastive learning (CL)-based semantic communication system. First, inspired by practical observations, we introduce the concept of semantic contrastive loss and propose a semantic contrastive coding (SemCC) approach that treats data corruption during transmission as a form of data augmentation within the CL framework. Moreover, we propose a semantic re-encoding (SemRE) operation, which uses a duplicate of the semantic encoder deployed at the receiver to guide the entire training process when the downstream model is inaccessible. Further, we design the training procedure for SemCC and SemRE approaches, respectively, to balance the semantic information and intricate details. Finally, simulations are performed to demonstrate the superiority of the proposed approaches over competing approaches. In particular, our approaches achieve a significant accuracy improvement of up to 53% on the CIFAR-10 dataset with a bandwidth compression ratio of 1/24, and also obtain comparable image reconstruction quality as the bandwidth compression ratio is improved.

Recently, semantic communication has been widely applied in wireless image transmission systems as it can prioritize the preservation of meaningful semantic information in images over the accuracy of transmitted symbols, leading to improved communication efficiency. However, existing semantic communication approaches still face limitations in achieving considerable inference performance in downstream AI tasks like image recognition, or balancing the inference performance with the quality of the reconstructed image at the receiver. Therefore, this paper proposes a contrastive learning (CL)-based semantic communication approach to overcome these limitations. Specifically, we regard the image corruption during transmission as a form of data augmentation in CL and leverage CL to reduce the semantic distance between the original and the corrupted reconstruction while maintaining the semantic distance among irrelevant images for better discrimination in downstream tasks. Moreover, we design a two-stage training procedure and the corresponding loss functions for jointly optimizing the semantic encoder and decoder to achieve a good trade-off between the performance of image recognition in the downstream task and reconstructed quality. Simulations are finally conducted to demonstrate the superiority of the proposed method over the competitive approaches. In particular, the proposed method can achieve up to 56% accuracy gain on the CIFAR10 dataset when the bandwidth compression ratio is 1/48.

This paper studies a multi-tier cache-aided relaying network, where the destination$D$is randomly located in the network and it requests files from the source$S$through the help of cache-aided base station (BS) and$N$relays. In this system, the multi-tier architecture imposes a significant impact on the system collaborative caching and file delivery, which brings a big challenge to the system performance evaluation and optimization. To address this problem, we first evaluate the system performance by deriving analytical outage probability expression, through fully taking into account the random location of the destination and different file delivery modes related to the file caching status. We then perform the asymptotic analysis on the system outage probability when the signal-to-noise ratio (SNR) is high, to enclose some important and meaningful insights on the network. We further optimize the caching strategies among the relays and BS, to improve the network outage probability. Simulations are performed to show the effectiveness of the derived analytical and asymptotic outage probability for the proposed caching strategy. In particular, the proposed caching is superior to the conventional caching strategies such as the most popular content (MPC) and equal probability caching (EPC) strategies.