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

arXiv: https://arxiv.org/abs/2606.31973 · HTML: https://mlsanity.com/paper/2606.31973/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [Deep Learning Enabled Semantic Communication Systems](https://mlsanity.com/paper/2006.10685/) (2020)
- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [Towards Semantic Communications: Deep Learning-Based Image Semantic Coding](https://mlsanity.com/paper/2208.04094/) (2022)
- [Task-Oriented Communications for NextG: End-to-End Deep Learning and AI Security Aspects](https://mlsanity.com/paper/2212.09668/) (2022)
- [Will 6G be Semantic Communications? Opportunities and Challenges from Task Oriented and Secure Communications to Integrated Sensing](https://mlsanity.com/paper/2401.01531/) (2024)
- [Encrypted Semantic Communication Using Adversarial Training for Privacy Preserving](https://mlsanity.com/paper/2209.09008/) (2022)
- [Secure Semantic Communications: Fundamentals and Challenges](https://mlsanity.com/paper/2301.01421/) (2023)
- [Semantic-Forward Relaying: A Novel Framework Towards 6G Cooperative Communications](https://mlsanity.com/paper/2310.07987/) (2023)
- [SemProtector: A Unified Framework for Semantic Protection in Deep Learning-based Semantic Communication Systems](https://mlsanity.com/paper/2309.01386/) (2023)
- [Distributed Task-Oriented Communication Networks with Multimodal Semantic Relay and Edge Intelligence](https://mlsanity.com/paper/2401.09904/) (2024)
- [Semantic Forwarding for Next Generation Relay Networks](https://mlsanity.com/paper/2401.17247/) (2024)

## Abstract (arXiv)

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.