Semantic Entropy Can Simultaneously Benefit Transmission Efficiency and Channel Security of Wireless Semantic Communications

TL;DR

This work tackles the dual challenge of transmission efficiency and security in wireless semantic communications. It introduces SemEntropy, a framework that uses semantic entropy to guide both feature selection and encryption, while adapting OFDM subcarrier allocation based on semantic importance. By combining a semantic information generator, entropy-guided encryption, and CSI-aware subcarrier mapping, SemEntropy achieves high semantic fidelity with substantially less data and strengthens security by increasing the attacker’s search space and degrading unauthorized BER. The results on reconstruction and classification tasks demonstrate competitive performance against strong baselines, particularly under low-SNR conditions, underscoring the practical potential of secure, efficient goal-oriented wireless communication.

Abstract

Recently proliferated deep learning-based semantic communications (DLSC) focus on how transmitted symbols efficiently convey a desired meaning to the destination. However, the sensitivity of neural models and the openness of wireless channels cause the DLSC system to be extremely fragile to various malicious attacks. This inspires us to ask a question: "Can we further exploit the advantages of transmission efficiency in wireless semantic communications while also alleviating its security disadvantages?". Keeping this in mind, we propose SemEntropy, a novel method that answers the above question by exploring the semantics of data for both adaptive transmission and physical layer encryption. Specifically, we first introduce semantic entropy, which indicates the expectation of various semantic scores regarding the transmission goal of the DLSC. Equipped with such semantic entropy, we can dynamically assign informative semantics to Orthogonal Frequency Division Multiplexing (OFDM) subcarriers with better channel conditions in a fine-grained manner. We also use the entropy to guide semantic key generation to safeguard communications over open wireless channels. By doing so, both transmission efficiency and channel security can be simultaneously improved. Extensive experiments over various benchmarks show the effectiveness of the proposed SemEntropy. We discuss the reason why our proposed method benefits secure transmission of DLSC, and also give some interesting findings, e.g., SemEntropy can keep the semantic accuracy remain 95% with 60% less transmission.

Figures (12)

• Figure 1: The general architecture of our SemEntropy. Controlling semantic selection and guiding semantic encryption and adaptive subcarrier allocation through semantic entropy.
• Figure 2: The detailed procedure of semantic information generator, semantic entropy-guided encryption and adaptive subcarrier allocation.
• Figure 3: The process of generating and exchanging semantic keys. We take the semantic scores generated by the semantic information generator and the semantic key SKey generated by traditional PLK.
• Figure 4: The inner architecture of the decoder.
• Figure 5: Effect of $\epsilon$ change on transmission delay for reconstruction tasks.