SignDeepSC: A Semantic Signature-based Approach for Robust Semantic Communication

2026-07-28

AI Summary

This work addresses the security vulnerability of deep semantic communication systems at the physical layer, where man-in-the-middle attacks can inject adversarial perturbations that induce semantic distortion. To counter this, the paper proposes SignDeepSC, a novel architecture that introduces a perceptron-inspired semantic signature transmitted over an auxiliary low-rate channel. Coupled with a cross-attention-based self-healing decoder and a feature shuffling mechanism, the system achieves robust semantic communication without requiring adversarial training. Evaluated under Rayleigh fading and AWGN channels against PGD attacks (ε=0.7, SNR=12 dB), SignDeepSC attains a BLEU-4 score of 0.237 and a BERT similarity of 0.646—significantly outperforming baseline methods while preserving performance in clean-channel conditions.

Abstract

Semantic communication systems such as deep semantic communication (DeepSC) offer high efficiency but are vulnerable to adversarial attacks on their underlying neural networks. We address a physical-layer man-in-the-middle (MitM) threat in which an adversary injects perturbations into the transmitted signal to distort its meaning. We propose SignDeepSC, an architectural defense that achieves adversarial robustness without requiring explicit adversarial example generation during training. The approach is built on a perceiver-inspired semantic signature, a compact vector summary of the source features transmitted over a separate low-rate auxiliary channel. This signature is used by a self-repairing decoder that leverages cross-attention to correct distortions and can additionally drive a scrambler that shuffles the feature layout. We evaluate SignDeepSC over Rayleigh fading and additive white Gaussian noise channels under both single-step fast gradient sign method (FGSM) and iterative projected gradient descent (PGD) attacks. Under PGD ($ε= 0.7$), at 12~dB signal-to-noise ratio with Rayleigh fading, SignDeepSC achieves a bilingual evaluation understudy (BLEU-4) score of 0.237 and bidirectional encoder representations from transformers (BERT) sentence similarity of 0.646, outperforming all baselines without degrading clean-channel performance, when the signature channel is well protected.

Problem

• semantic communication
• adversarial attacks
• man-in-the-middle
• neural network robustness
• signal distortion

Innovation

• semantic signature
• adversarial robustness
• self-repairing decoder
• cross-attention
• semantic communication