A Secure Semantic Communication System Based on Knowledge Graph

TL;DR

This work addresses secure semantic communication by encoding textual content into a knowledge graph and protecting it with a hybrid, frequency-domain encryption that combines constellation diagonal transformation and MP-WFRFT. The sender extracts semantic structure via LDA-KMeans clustering and KG construction (CRF, Word2Vec, CN-DBpedia, PageRank), then encrypts the KG before transmission; the receiver decrypts and recovers text with a Transformer-based model. A novel security metric, Detection Failure Probability (DFP), and BLEU-based semantic fidelity demonstrate that the legitimate receiver achieves high semantic accuracy (BLEU ≈ 0.9) while the eavesdropper remains around or below 0.3, with up to ~20% relative security gain over baselines. The approach leverages a shared knowledge base and KG interpretability to enhance security without excessive computational burden, showing robust performance across varying SNRs and channel conditions.

Abstract

This study proposes a novel approach to ensure the security of textual data transmission in a semantic communication system. In the proposed system, a sender transmits textual information to a receiver, while a potential eavesdropper attempts to intercept the information. At the sender side, the text is initially preprocessed, where each sentence is annotated with its corresponding topic, and subsequently extracted into a knowledge graph. To achieve the secure transmission of the knowledge graph, we propose a channel encryption scheme that integrates constellation diagonal transformation with multi-parameter weighted fractional Fourier transform (MP-WFRFT). At the receiver side, the textual data is first decrypted, and then recovered via a transformer model. Experimental results demonstrate that the proposed method reduces the probability of information compromise. The legitimate receiver achieves a Bilingual Evaluation Understudy (BLEU) score of 0.9, whereas the BLEU score of the eavesdropper remains below 0.3. Compared to the baselines, the proposed method can improve the security by up to 20%.

Figures (12)

• Figure 1: The architecture of the proposed secure semantic communication system.
• Figure 2: Text-based knowledge graph construction and encryption Processing.
• Figure 3: Flow diagram of data preprocessing.
• Figure 4: Architecture of knowledge graph construction.
• Figure 5: A visualization example of knowledge graph.