Contrastive Learning and Adversarial Disentanglement for Privacy-Aware Task-Oriented Semantic Communication

TL;DR

This paper introduces CLAD, a novel method combining contrastive learning and adversarial disentanglement to improve privacy and efficiency in task-oriented semantic communication for 6G-IoT, with a new metric called IRI.

Contribution

The paper proposes CLAD, a new approach that effectively disentangles task-relevant and irrelevant information, and introduces IRI to quantify minimality of encoded features.

Findings

CLAD outperforms existing methods in semantic extraction and task accuracy.

CLAD enhances privacy preservation in 6G-IoT communications.

IRI correlates with privacy and bandwidth efficiency improvements.

Abstract

Task-oriented semantic communication systems have emerged as a promising approach to achieving efficient and intelligent data transmission in next-generation networks, where only information relevant to a specific task is communicated. This is particularly important in 6G-enabled Internet of Things (6G-IoT) scenarios, where bandwidth constraints, latency requirements, and data privacy are critical. However, existing methods struggle to fully disentangle task-relevant and task-irrelevant information, leading to privacy concerns and suboptimal performance. To address this, we propose an information-bottleneck inspired method, named CLAD (contrastive learning and adversarial disentanglement). CLAD utilizes contrastive learning to effectively capture task-relevant features while employing adversarial disentanglement to discard task-irrelevant information. Additionally, due to the absence of reliable and reproducible methods to quantify the minimality of encoded feature vectors, we introduce the Information Retention Index (IRI), a comparative metric used as a proxy for the mutual information between the encoded features and the input. The IRI reflects how minimal and informative the representation is, making it highly relevant for privacy-preserving and bandwidth-efficient 6G-IoT systems. Extensive experiments demonstrate that CLAD outperforms state-of-the-art baselines in terms of semantic extraction, task performance, privacy preservation, and IRI, making it a promising building block for responsible, efficient and trustworthy 6G-IoT services.