← 研踪 PaperTrailarXiv:2611.02938 · v1
Leakage-Aware Encrypted Semantic Communication with Key-Conditioned Signal Perturbation
首次提交 2026-11-02 19:05
版本更新 2026-11-02 19:05
雷达观测 2026-11-04 23:42
摘要
Encrypted semantic communication systems protect transmitted messages by inserting key-conditioned modules into a deep-learning semantic communication pipeline, but existing designs rely on a fixed adversarial weight and operate mainly at the semantic-feature level. We propose two changes to the encrypted semantic communication system (ESCS): a key-conditioned signal-domain perturbation layer, called learned adversarial perturbation injection (LAPI), and an information noise-contrastive estimation (InfoNCE)-guided adaptive training rule that {adds an adaptive leakage penalty alongside the fixed adversarial objective} using an InfoNCE-based proxy for mutual information leakage. Experiments on the Europarl corpus over additive white Gaussian noise (AWGN) and Rayleigh fading channels show that InfoNCE-guided training is the primary source of eavesdropper suppression, reducing the eavesdropper's bilingual evaluation understudy (BLEU) score to approximately 0.07 at high signal-to-noise ratio (SNR). Adding LAPI to the InfoNCE-guided objective further lowers the InfoNCE-estimated leakage by 5-9% with low measured inference overhead, while its impact on legitimate-receiver BLEU depends on channel conditions. The two mechanisms operate on different parts of the pipeline and can be jointly applied.
作者备注：Accepted for presentation at IEEE GLOBECOM 2026
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-02 19:05 · 最新观测版本
Leakage-Aware Encrypted Semantic Communication with Key-Conditioned Signal Perturbation
Encrypted semantic communication systems protect transmitted messages by inserting key-conditioned modules into a deep-learning semantic communication pipeline, but existing designs rely on a fixed adversarial weight and operate mainly at the semantic-feature level. We propose two changes to the encrypted semantic communication system (ESCS): a key-conditioned signal-domain perturbation layer, called learned adversarial perturbation injection (LAPI), and an information noise-contrastive estimation (InfoNCE)-guided adaptive training rule that {adds an adaptive leakage penalty alongside the fixed adversarial objective} using an InfoNCE-based proxy for mutual information leakage. Experiments on the Europarl corpus over additive white Gaussian noise (AWGN) and Rayleigh fading channels show that InfoNCE-guided training is the primary source of eavesdropper suppression, reducing the eavesdropper's bilingual evaluation understudy (BLEU) score to approximately 0.07 at high signal-to-noise ratio (SNR). Adding LAPI to the InfoNCE-guided objective further lowers the InfoNCE-estimated leakage by 5-9% with low measured inference overhead, while its impact on legitimate-receiver BLEU depends on channel conditions. The two mechanisms operate on different parts of the pipeline and can be jointly applied.
查看此版本解读 →查看此版本原文 ↗