Distributionally Robust Wireless Semantic Communication with Large AI Models

2025-05-28

AI Summary

Traditional bit-level communication struggles to simultaneously achieve high efficiency and robustness for 6G’s massive-data, ultra-low-latency transmission requirements, while existing semantic communication (SemCom) approaches exhibit limited generalization and are highly sensitive to semantic and channel noise. Method: We propose WaSeCom, an end-to-end SemCom framework that (i) introduces Wasserstein distributionally robust optimization—first applied in SemCom—to jointly model semantic distortion and channel perturbations, providing theoretically guaranteed generalization; and (ii) integrates large language models with visual encoders, enabling semantic-aware channel adaptation and joint training. Contribution/Results: Experiments demonstrate that WaSeCom significantly enhances resilience against both stochastic noise and adversarial perturbations in image and text tasks. Moreover, it maintains stable semantic fidelity under dynamic channel conditions, thereby overcoming critical bottlenecks in SemCom robustness and generalization.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• 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
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

6G wireless systems are expected to support massive volumes of data with ultra-low latency. However, conventional bit-level transmission strategies cannot support the efficiency and adaptability required by modern, data-intensive applications. The concept of semantic communication (SemCom) addresses this limitation by focusing on transmitting task-relevant semantic information instead of raw data. While recent efforts incorporating deep learning and large-scale AI models have improved SemCom's performance, existing systems remain vulnerable to both semantic-level and transmission-level noise because they often rely on domain-specific architectures that hinder generalizability. In this paper, a novel and generalized semantic communication framework called WaSeCom is proposed to systematically address uncertainty and enhance robustness. In particular, Wasserstein distributionally robust optimization is employed to provide resilience against semantic misinterpretation and channel perturbations. A rigorous theoretical analysis is performed to establish the robust generalization guarantees of the proposed framework. Experimental results on image and text transmission demonstrate that WaSeCom achieves improved robustness under noise and adversarial perturbations. These results highlight its effectiveness in preserving semantic fidelity across varying wireless conditions.

Problem

• Enhancing robustness in semantic communication against noise
• Addressing uncertainty in wireless semantic transmission systems
• Improving semantic fidelity across varying wireless conditions

Innovation

• Wasserstein robust optimization for semantic resilience
• Generalized semantic framework enhancing adaptability
• Theoretical guarantees for robust generalization