AHCI RESEARCH GROUP
Publications
Papers published in international journals,
proceedings of conferences, workshops and books.
OUR RESEARCH
Scientific Publications
How to
Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
2024
Truong, V. T.; Le, H. D.; Le, L. B.
Trust-Free Blockchain Framework for AI-Generated Content Trading and Management in Metaverse Journal Article
In: IEEE Access, vol. 12, pp. 41815–41828, 2024, ISSN: 21693536 (ISSN).
Abstract | Links | BibTeX | Tags: AI-generated content, AI-generated content (AIGC), Artificial intelligence, Asset management, Assets management, Block-chain, Blockchain, Commerce, Content distribution networks, Cyber-attacks, Decentralised, Decentralized application, Digital asset management, Digital system, Generative AI, Metaverse, Metaverses, Plagiarism, Security, Trustless service, Virtual Reality
@article{truong_trust-free_2024,
title = {Trust-Free Blockchain Framework for AI-Generated Content Trading and Management in Metaverse},
author = {V. T. Truong and H. D. Le and L. B. Le},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85188472793&doi=10.1109%2fACCESS.2024.3376509&partnerID=40&md5=301939c1faef0c5a7b56d9feadce27ee},
doi = {10.1109/ACCESS.2024.3376509},
issn = {21693536 (ISSN)},
year = {2024},
date = {2024-01-01},
journal = {IEEE Access},
volume = {12},
pages = {41815–41828},
abstract = {The rapid development of the metaverse and generative Artificial Intelligence (GAI) has led to the emergence of AI-Generated Content (AIGC). Unlike real-world products, AIGCs are represented as digital files, thus vulnerable to plagiarism and leakage on the Internet. In addition, the trading of AIGCs in the virtual world is prone to various trust issues between the involved participants. For example, some customers may try to avoid the payment after receiving the desired AIGC products, or the content sellers refuse to grant the products after obtaining the license fee. Existing digital asset management (DAM) systems often rely on a trusted third-party authority to mitigate these issues. However, this might lead to centralization problems such as the single-point-of-failure (SPoF) when the third parties are under attacks or being malicious. In this paper, we propose MetaTrade, a blockchain-empowered DAM framework that is designed to tackle these urgent trust issues, offering secured AIGC trading and management in the trustless metaverse environment. MetaTrade eliminates the role of the trusted third party, without requiring trust assumptions among participants. Numerical results show that MetaTrade offers higher performance and lower trading cost compared to existing platforms, while security analysis reveals that the framework is resilient against plagiarism, SPoF, and trust-related attacks. To showcase the feasibility of the design, a decentralized application (DApp) has been built on top of MetaTrade as a marketplace for metaverse AIGCs. © 2013 IEEE.},
keywords = {AI-generated content, AI-generated content (AIGC), Artificial intelligence, Asset management, Assets management, Block-chain, Blockchain, Commerce, Content distribution networks, Cyber-attacks, Decentralised, Decentralized application, Digital asset management, Digital system, Generative AI, Metaverse, Metaverses, Plagiarism, Security, Trustless service, Virtual Reality},
pubstate = {published},
tppubtype = {article}
}
The rapid development of the metaverse and generative Artificial Intelligence (GAI) has led to the emergence of AI-Generated Content (AIGC). Unlike real-world products, AIGCs are represented as digital files, thus vulnerable to plagiarism and leakage on the Internet. In addition, the trading of AIGCs in the virtual world is prone to various trust issues between the involved participants. For example, some customers may try to avoid the payment after receiving the desired AIGC products, or the content sellers refuse to grant the products after obtaining the license fee. Existing digital asset management (DAM) systems often rely on a trusted third-party authority to mitigate these issues. However, this might lead to centralization problems such as the single-point-of-failure (SPoF) when the third parties are under attacks or being malicious. In this paper, we propose MetaTrade, a blockchain-empowered DAM framework that is designed to tackle these urgent trust issues, offering secured AIGC trading and management in the trustless metaverse environment. MetaTrade eliminates the role of the trusted third party, without requiring trust assumptions among participants. Numerical results show that MetaTrade offers higher performance and lower trading cost compared to existing platforms, while security analysis reveals that the framework is resilient against plagiarism, SPoF, and trust-related attacks. To showcase the feasibility of the design, a decentralized application (DApp) has been built on top of MetaTrade as a marketplace for metaverse AIGCs. © 2013 IEEE.
Lee, S.; Park, W.; Lee, K.
Building Knowledge Base of 3D Object Assets Using Multimodal LLM AI Model Proceedings Article
In: Int. Conf. ICT Convergence, pp. 416–418, IEEE Computer Society, 2024, ISBN: 21621233 (ISSN); 979-835036463-7 (ISBN).
Abstract | Links | BibTeX | Tags: 3D object, Asset management, Content services, Exponentials, Information Management, Knowledge Base, Language Model, Large language model, LLM, Multi-modal, Multi-Modal AI, Reusability, Visual effects, XR
@inproceedings{lee_building_2024,
title = {Building Knowledge Base of 3D Object Assets Using Multimodal LLM AI Model},
author = {S. Lee and W. Park and K. Lee},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85217636269&doi=10.1109%2fICTC62082.2024.10827434&partnerID=40&md5=581ee8ca50eb3dae15dc9675971cf428},
doi = {10.1109/ICTC62082.2024.10827434},
isbn = {21621233 (ISSN); 979-835036463-7 (ISBN)},
year = {2024},
date = {2024-01-01},
booktitle = {Int. Conf. ICT Convergence},
pages = {416–418},
publisher = {IEEE Computer Society},
abstract = {The proliferation of various XR (eXtended Reality) services and the increasing incorporation of visual effects into existing content services have led to an exponential rise in the demand for 3D object assets. This paper describes an LLM (Large Language Model)-based multimodal AI model pipeline that can be applied to a generative AI model for creating new 3D objects or restructuring the asset management system to enhance the reusability of existing 3D objects. By leveraging a multimodal AI model, we derived descriptive text for assets such as 3D object, 2D image at a human-perceptible level, rather than mere data, and subsequently used an LLM to generate knowledge triplets for constructing an asset knowledge base. The applicability of this pipeline was verified using actual 3D objects from a content production company. Future work will focus on improving the quality of the generated knowledge triplets themselves by training the multimodal AI model with real-world content usage assets. © 2024 IEEE.},
keywords = {3D object, Asset management, Content services, Exponentials, Information Management, Knowledge Base, Language Model, Large language model, LLM, Multi-modal, Multi-Modal AI, Reusability, Visual effects, XR},
pubstate = {published},
tppubtype = {inproceedings}
}
The proliferation of various XR (eXtended Reality) services and the increasing incorporation of visual effects into existing content services have led to an exponential rise in the demand for 3D object assets. This paper describes an LLM (Large Language Model)-based multimodal AI model pipeline that can be applied to a generative AI model for creating new 3D objects or restructuring the asset management system to enhance the reusability of existing 3D objects. By leveraging a multimodal AI model, we derived descriptive text for assets such as 3D object, 2D image at a human-perceptible level, rather than mere data, and subsequently used an LLM to generate knowledge triplets for constructing an asset knowledge base. The applicability of this pipeline was verified using actual 3D objects from a content production company. Future work will focus on improving the quality of the generated knowledge triplets themselves by training the multimodal AI model with real-world content usage assets. © 2024 IEEE.