Efficient Semantic-aware Encryption for Secure Communications in Intelligent Connected Vehicles

TL;DR

This paper introduces ESAE, a semantic-aware encryption mechanism for secure vehicle communication that reduces key management complexity and enhances security by leveraging semantic reciprocity and deep learning-based key pre-processing.

Contribution

The paper presents a novel encryption scheme integrating cryptography with semantic communication, using semantic reciprocity and YOLO-v10 for consistent key generation in intelligent connected vehicles.

Findings

ESAE effectively secures semantic transmission in ICVs.

The semantic-aware key pre-processing ensures key consistency.

Experimental results demonstrate ESAE's robustness under various wireless conditions.

Abstract

Semantic communication (SemCom) significantly improves inter-vehicle interactions in intelligent connected vehicles (ICVs) within limited wireless spectrum. However, the open nature of wireless communications introduces eavesdropping risks. To mitigate this, we propose the Efficient Semantic-aware Encryption (ESAE) mechanism, integrating cryptography into SemCom to secure semantic transmission without complex key management. ESAE leverages semantic reciprocity between source and reconstructed information from past communications to independently generate session keys at both ends, reducing key transmission costs and associated security risks. Additionally, ESAE introduces a semantic-aware key pre-processing method (SA-KP) using the YOLO-v10 model to extract consistent semantics from bit-level diverse yet semantically identical content, ensuring key consistency. Experimental results validate ESAE's effectiveness and feasibility under various wireless conditions, with key performance factors discussed.