Artificial Intelligence-Based Cybersecurity for the Metaverse: Research Challenges and Opportunities
The metaverse, known as the next-generation 3D Internet, represents virtual environments that mirror the physical world. It is supported by innovative technologies such as digital twins and extended reality (XR), which elevate user experiences across various fields. However, the metaverse also introduces significant cybersecurity and privacy challenges that remain underexplored. Due to its complex multi-tech infrastructure, the metaverse requires sophisticated, automated, and intelligent cybersecurity measures to mitigate emerging threats effectively. Therefore, this paper is the first to explore Artificial Intelligence (AI)-driven cybersecurity techniques for the metaverse, examining academic and industrial perspectives. First, we provide an overview of the metaverse, presenting a detailed system model, diverse use cases, and insights into its current industrial status. We then present attack models and cybersecurity threats derived from the unique characteristics and technologies of the metaverse. Next, we review AI-driven cybersecurity solutions based on three critical aspects: User authentication, intrusion detection systems (IDS), and the security of digital assets, specifically for Blockchain and Non-fungible Tokens (NFTs). Finally, we highlight challenges and suggest future research opportunities to enhance metaverse security, privacy, and digital asset transactions.
Authors
- Khouloud Eledlebi (ORCID: https://orcid.org/0000-0002-4355-4041)
- Kim‐Kwang Raymond Choo (ORCID: https://orcid.org/0000-0001-9208-5336)
- Mohamed Jamal Zemerly (ORCID: https://orcid.org/0000-0003-1845-5946)
- Paul D. Yoo (ORCID: https://orcid.org/0000-0001-7665-8616)
- Chan Yeob Yeun (ORCID: https://orcid.org/0000-0002-1398-952X)
- Deepak Puthal (ORCID: https://orcid.org/0000-0002-8332-278X)
- Kamal Taha (ORCID: https://orcid.org/0000-0002-6674-4614)
- Ernesto Damiani (ORCID: https://orcid.org/0000-0002-9557-6496)
- Man‐Sung Yim (ORCID: https://orcid.org/0000-0001-8581-1635)
- Abeer Awadallah (ORCID: https://orcid.org/0000-0002-0883-6625)
- Tae‐Yeon Kim (ORCID: https://orcid.org/0000-0003-4743-6023)
Institutions
- University of London (GB)
- Magadh University (IN)
- Indian Institute of Management Ahmedabad (IN)
- University of East London (GB)
- Korea Advanced Institute of Science and Technology (KR)
- Khalifa University of Science and Technology (AE)
- Indian Institute of Management Bodh Gaya
- The University of Texas at San Antonio (US)
Publication Details
- Journal
- IEEE Communications Surveys & Tutorials
- Published
- 2024-08-12
- DOI
- https://doi.org/10.1109/comst.2024.3442475
- Citations
- 52
- Primary Topic
- Advanced Malware Detection Techniques
- Type
- article
- Field-Weighted Citation Impact
- 18.21