Towards Secure Semantic Transmission In the Era of GenAI: A Diffusion-based Framework

2025-05-09

AI Summary

Semantic communication systems face emerging security threats—including semantic-layer eavesdropping and adversarial interference—in the generative AI era. To address these challenges, this paper pioneers the integration of denoising diffusion probabilistic models (DDPMs) into semantic communication security, proposing a noise-coordinated semantic transmission framework. The method unifies artificial and channel noise modeling: controlled noise is injected during the forward diffusion process to jointly mitigate eavesdropping and interference, while the legitimate receiver reconstructs high-fidelity semantics via reverse denoising. Crucially, adversarial interference is explicitly modeled as a controllable noise variable within the diffusion process. Experimental results demonstrate that, under concurrent eavesdropping and interference, the framework reduces semantic misclassification rate by over 40%, significantly enhancing semantic fidelity and robustness.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Adversarial Learning & Robustness
• Natural Language Processing: Safety and Robustness

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Semantic communication, due to its focus on the transmitting meaning rather than the raw bit data, poses unique security challenges compared to the traditional communication systems. In particular, semantic communication systems are vulnerable to the malicious attacks that focus on the semantic layer, with the intention of understanding or distorting the intended meaning of the transmitted privacy data. Diffusion models, a class of generative artificial intelligence (GenAI), are well-suited for ensuring data security to attack. Through iteratively adding and then removing noise, diffusion models can generate meaningful information despite the presence of the unknown noise. This article proposes a diffusion-based framework to enhance the security of semantic transmission for the attacks including eavesdropping and jamming. Specifically, the proposed framework incorporates both the artificial noise and natural channel noise into the forward process of the diffusion models during the semantic transmission, with the reverse process used to remove noise at the legitimate receiver. In the eavesdropping scenarios, the artificial noise is the friendly noise designed to prevent semantic eavesdropping. In the jamming scenarios, the artificial noise is the malicious jamming generated by the jammer, which disrupts the semantic transmission. The case studies show that the proposed diffusion-based framework is promising in securing the semantic transmission. We also consolidate several broad research directions associated with the proposed framework.

Problem

• Enhancing security in semantic communication systems
• Protecting privacy data from semantic layer attacks
• Using diffusion models to counter eavesdropping and jamming

Innovation

• Diffusion models enhance semantic transmission security
• Artificial noise prevents eavesdropping in semantic communication
• Reverse process removes noise at legitimate receiver