Can Knowledge Improve Security? A Coding-Enhanced Jamming Approach for Semantic Communication

TL;DR

This work addresses securing semantic communications without relying on secret-key channels by introducing a coding-enhanced jamming mechanism that leverages a privately shared knowledge base. The transmitter creates an outer semantic code $Y_1$ and an inner jamming code $Y_2$, superposed as $Y= ext{PAC}$, with a power allocation coefficient $a$ that explicitly controls security; Bob can cancel $Y_2$ using the shared private information, while Eve cannot. A novel training framework using an nHSIC regularizer reduces dependency between $Y_1$ and $Y_2$, enabling effective jamming without leaking semantic content. Experimental results show security comparable to state-of-the-art approaches while delivering >1 dB gains in Bob’s reconstruction across SNRs and compression ratios, and demonstrate practical deployability by avoiding secret-key transmission and enabling explicit security control. The approach is end-to-end digital SemCom, uses CNN-based encoders/decoders, and can extend to other modalities and analog DeepJSCC settings with adaptive PAC optimization.

Abstract

As semantic communication (SemCom) attracts growing attention as a novel communication paradigm, ensuring the security of transmitted semantic information over open wireless channels has become a critical issue. However, traditional encryption methods often introduce significant additional communication overhead to maintain reliability, and conventional learning-based secure SemCom methods typically rely on a channel capacity advantage for the legitimate receiver, which is challenging to guarantee in real-world scenarios. In this paper, we propose a coding-enhanced jamming method that eliminates the need to transmit a secret key by utilizing shared knowledge, which may be part of the training set of the SemCom system, between the legitimate receiver and the transmitter. Specifically, we leverage the shared private knowledge base to generate a set of private digital codebooks in advance using neural network (NN)-based encoders. For each transmission, we encode the transmitted data into a digital sequence Y1 and associate Y1 with a sequence randomly picked from the private codebook, denoted as Y2, through superposition coding. Here, Y1 serves as the outer code and Y2 as the inner code. By optimizing the power allocation between the inner and outer codes, the legitimate receiver can reconstruct the transmitted data using successive decoding based on the shared index of Y2, while the eavesdropper's decoding performance is severely degraded, potentially to the point of random guessing. Experimental results demonstrate that our method achieves security comparable to state-of-the-art approaches while significantly improving the reconstruction performance of the legitimate receiver by more than 1 dB across varying channel signal-to-noise ratios (SNRs) and compression ratios.

Figures (16)

• Figure 1: The proposed secure digital SemCom system with coding-enhanced jamming.
• Figure 2: The network architecture of the outer and inner semantic encoders.
• Figure 3: The network architecture of the NN-based 4-QAM modulator.
• Figure 4: The network architecture of the semantic decoder.
• Figure 5: The 4-QAM outer constellation map.