---
title: "Semantic Leakage and Privacy Preservation in Relay-Assisted Semantic Communications"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2606.31973v1"
permalink: "https://feed.astralor.com/items/itm_2d2b9bc503ca810b5806127a"
published: "2026-06-30T17:15:23.000Z"
score: 55
channel: "ai"
tags: ["Relay-assisted","Adversarial Training","Semantic Communication","Privacy Protection"]
---

# Semantic Leakage and Privacy Preservation in Relay-Assisted Semantic Communications

## At a glance

Semantic communication prioritizes task-relevant information for efficiency, but relay nodes introduce privacy risks: a relay can reliably infer semantics and reconstruct signals without accessing source data. This paper proposes an iterative adversarial training framework that accounts for a strong adaptive eavesdropper at the relay, optimizing representations to preserve high decoding performance at the intended receiver while degrading semantic inference at the relay. The approach significantly widens the semantic accuracy gap between legitimate receiver and eavesdropper across various channel conditions, achieving protection stealthily without compromising reconstruction fidelity.

## Key points

- A relay node can achieve semantic inference and signal reconstruction comparable to the legitimate receiver without access to source data, revealing fundamental privacy vulnerability of semantic representations.
- An iterative adversarial training framework is proposed, explicitly modeling a strong adaptive eavesdropper at the relay and alternating optimization between eavesdropping function and legitimate system.
- Learned representations preserve semantic decoding performance at the legitimate receiver while significantly degrading semantic inference at the relay, remaining robust across varying channel conditions.
- Protection is achieved in a stealthy manner: reconstruction fidelity is maintained while semantic leakage is selectively suppressed.

## Full text

Semantic communication (SemCom) has emerged as a promising paradigm in which the transmission of task-relevant information is prioritized over raw data, enabling efficient and robust communication under resource and channel constraints. In this paper, the privacy implications of relay-assisted SemCom systems are studied, where the intermediate relay node operates directly on learned latent representations. It is shown that the relay, even without access to source data, can reliably infer semantic meaning and reconstruct signals with performance comparable to that of the legitimate receiver, revealing a fundamental privacy vulnerability of semantic representations. To address this issue, an iterative adversarial training framework is proposed in which a strong, adaptively trained eavesdropper at the relay is explicitly accounted for. The proposed approach alternates between optimizing the relay's eavesdropping function and the legitimate system, resulting in representations that preserve semantic decoding performance at the intended receiver while degrading semantic inference at the relay. The semantic accuracy gap between the legitimate receiver and the eavesdropper is significantly enlarged across channel conditions. Importantly, this protection is achieved in a stealthy manner, with high reconstruction fidelity maintained while semantic leakage is selectively suppressed.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_2d2b9bc503ca810b5806127a