Blockchain-aided secure semantic communication for AI-generated content in metaverse

The construction of virtual transportation networks requires massive data to be transmitted from edge devices to Virtual Service Providers (VSP) to facilitate circulations between the physical and virtual domains in Metaverse. Leveraging semantic communication for reducing information redundancy, VS...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin, Yijing, Du, Hongyang, Niyato, Dusit, Nie, Jiangtian, Zhang, Jiayi, Cheng, Yanyu, Yang, Zhaohui
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10356/173645
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-173645
record_format dspace
spelling sg-ntu-dr.10356-1736452024-02-23T15:35:41Z Blockchain-aided secure semantic communication for AI-generated content in metaverse Lin, Yijing Du, Hongyang Niyato, Dusit Nie, Jiangtian Zhang, Jiayi Cheng, Yanyu Yang, Zhaohui School of Computer Science and Engineering Alibaba-NTU Singapore Joint Research Institute Computer and Information Science Metaverse Blockchain The construction of virtual transportation networks requires massive data to be transmitted from edge devices to Virtual Service Providers (VSP) to facilitate circulations between the physical and virtual domains in Metaverse. Leveraging semantic communication for reducing information redundancy, VSPs can receive semantic data from edge devices to provide varied services through advanced techniques, e.g., AI-Generated Content (AIGC), for users to explore digital worlds. But the use of semantic communication raises a security issue because attackers could send malicious semantic data with similar semantic information but different desired content to break Metaverse services and cause wrong output of AIGC. Therefore, in this paper, we first propose a blockchain-aided semantic communication framework for AIGC services in virtual transportation networks to facilitate interactions of the physical and virtual domains among VSPs and edge devices. We illustrate a training-based targeted semantic attack scheme to generate adversarial semantic data by various loss functions. We also design a semantic defense scheme that uses the blockchain and zero-knowledge proofs to tell the difference between the semantic similarities of adversarial and authentic semantic data and to check the authenticity of semantic data transformations. Simulation results show that the proposed defense method can reduce the semantic similarity of the adversarial semantic data and the authentic ones by up to 30% compared with the attack scheme. AI Singapore Info-communications Media Development Authority (IMDA) National Research Foundation (NRF) Published version This work was supported in part by the National Research Foundation (NRF), in part by the Singapore and Infocomm Media Development Authority through the Future Communications Research Development Programme (FCP), in part by DSO National Laboratories through the AI Singapore Programme under AISG Award AISG2-RP-2020-019, in part by the Energy Research Test-Bed and Industry Partnership Funding Initiative, part of the Energy Grid (EG) 2.0 Programme, and in part by the DesCartes and the Campus for Research Excellence and Technological Enterprise (CREATE) Programme. 2024-02-20T08:42:25Z 2024-02-20T08:42:25Z 2023 Journal Article Lin, Y., Du, H., Niyato, D., Nie, J., Zhang, J., Cheng, Y. & Yang, Z. (2023). Blockchain-aided secure semantic communication for AI-generated content in metaverse. IEEE Open Journal of the Computer Society, 4, 72-83. https://dx.doi.org/10.1109/OJCS.2023.3260732 2644-1268 https://hdl.handle.net/10356/173645 10.1109/OJCS.2023.3260732 2-s2.0-85151529281 4 72 83 en AISG2-RP-2020-019 IEEE Open Journal of the Computer Society © 2023 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
Metaverse
Blockchain
spellingShingle Computer and Information Science
Metaverse
Blockchain
Lin, Yijing
Du, Hongyang
Niyato, Dusit
Nie, Jiangtian
Zhang, Jiayi
Cheng, Yanyu
Yang, Zhaohui
Blockchain-aided secure semantic communication for AI-generated content in metaverse
description The construction of virtual transportation networks requires massive data to be transmitted from edge devices to Virtual Service Providers (VSP) to facilitate circulations between the physical and virtual domains in Metaverse. Leveraging semantic communication for reducing information redundancy, VSPs can receive semantic data from edge devices to provide varied services through advanced techniques, e.g., AI-Generated Content (AIGC), for users to explore digital worlds. But the use of semantic communication raises a security issue because attackers could send malicious semantic data with similar semantic information but different desired content to break Metaverse services and cause wrong output of AIGC. Therefore, in this paper, we first propose a blockchain-aided semantic communication framework for AIGC services in virtual transportation networks to facilitate interactions of the physical and virtual domains among VSPs and edge devices. We illustrate a training-based targeted semantic attack scheme to generate adversarial semantic data by various loss functions. We also design a semantic defense scheme that uses the blockchain and zero-knowledge proofs to tell the difference between the semantic similarities of adversarial and authentic semantic data and to check the authenticity of semantic data transformations. Simulation results show that the proposed defense method can reduce the semantic similarity of the adversarial semantic data and the authentic ones by up to 30% compared with the attack scheme.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Lin, Yijing
Du, Hongyang
Niyato, Dusit
Nie, Jiangtian
Zhang, Jiayi
Cheng, Yanyu
Yang, Zhaohui
format Article
author Lin, Yijing
Du, Hongyang
Niyato, Dusit
Nie, Jiangtian
Zhang, Jiayi
Cheng, Yanyu
Yang, Zhaohui
author_sort Lin, Yijing
title Blockchain-aided secure semantic communication for AI-generated content in metaverse
title_short Blockchain-aided secure semantic communication for AI-generated content in metaverse
title_full Blockchain-aided secure semantic communication for AI-generated content in metaverse
title_fullStr Blockchain-aided secure semantic communication for AI-generated content in metaverse
title_full_unstemmed Blockchain-aided secure semantic communication for AI-generated content in metaverse
title_sort blockchain-aided secure semantic communication for ai-generated content in metaverse
publishDate 2024
url https://hdl.handle.net/10356/173645
_version_ 1794549307442987008