Enhancing Privacy in Semantic Communication over Wiretap Channels leveraging Differential Privacy

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Weixuan, Tang, Shunpu, Yang, Qianqian, Shi, Zhiguo, Niyato, Dusit
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908351406800896
author Chen, Weixuan
Tang, Shunpu
Yang, Qianqian
Shi, Zhiguo
Niyato, Dusit
author_facet Chen, Weixuan
Tang, Shunpu
Yang, Qianqian
Shi, Zhiguo
Niyato, Dusit
contents Semantic communication (SemCom) improves transmission efficiency by focusing on task-relevant information. However, transmitting semantic-rich data over insecure channels introduces privacy risks. This paper proposes a novel SemCom framework that integrates differential privacy (DP) mechanisms to protect sensitive semantic features. This method employs the generative adversarial network (GAN) inversion technique to extract disentangled semantic features and uses neural networks (NNs) to approximate the DP application and removal processes, effectively mitigating the non-invertibility issue of DP. Additionally, an NN-based encryption scheme is introduced to strengthen the security of channel inputs. Simulation results demonstrate that the proposed approach effectively prevents eavesdroppers from reconstructing sensitive information by generating chaotic or fake images, while ensuring high-quality image reconstruction for legitimate users. The system exhibits robust performance across various privacy budgets and channel conditions, achieving an optimal balance between privacy protection and reconstruction fidelity.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18581
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Privacy in Semantic Communication over Wiretap Channels leveraging Differential Privacy
Chen, Weixuan
Tang, Shunpu
Yang, Qianqian
Shi, Zhiguo
Niyato, Dusit
Cryptography and Security
Image and Video Processing
Semantic communication (SemCom) improves transmission efficiency by focusing on task-relevant information. However, transmitting semantic-rich data over insecure channels introduces privacy risks. This paper proposes a novel SemCom framework that integrates differential privacy (DP) mechanisms to protect sensitive semantic features. This method employs the generative adversarial network (GAN) inversion technique to extract disentangled semantic features and uses neural networks (NNs) to approximate the DP application and removal processes, effectively mitigating the non-invertibility issue of DP. Additionally, an NN-based encryption scheme is introduced to strengthen the security of channel inputs. Simulation results demonstrate that the proposed approach effectively prevents eavesdroppers from reconstructing sensitive information by generating chaotic or fake images, while ensuring high-quality image reconstruction for legitimate users. The system exhibits robust performance across various privacy budgets and channel conditions, achieving an optimal balance between privacy protection and reconstruction fidelity.
title Enhancing Privacy in Semantic Communication over Wiretap Channels leveraging Differential Privacy
topic Cryptography and Security
Image and Video Processing
url https://arxiv.org/abs/2504.18581