Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses
arXiv:2210.13289 · doi:10.1145/3614426
Abstract
Metaverse is expected to emerge as a new paradigm for the next-generation Internet, providing fully immersive and personalised experiences to socialize, work, and play in self-sustaining and hyper-spatio-temporal virtual world(s). The advancements in different technologies like augmented reality, virtual reality, extended reality (XR), artificial intelligence (AI), and 5G/6G communication will be the key enablers behind the realization of AI-XR metaverse applications. While AI itself has many potential applications in the aforementioned technologies (e.g., avatar generation, network optimization, etc.), ensuring the security of AI in critical applications like AI-XR metaverse applications is profoundly crucial to avoid undesirable actions that could undermine users' privacy and safety, consequently putting their lives in danger. To this end, we attempt to analyze the security, privacy, and trustworthiness aspects associated with the use of various AI techniques in AI-XR metaverse applications. Specifically, we discuss numerous such challenges and present a taxonomy of potential solutions that could be leveraged to develop secure, private, robust, and trustworthy AI-XR applications. To highlight the real implications of AI-associated adversarial threats, we designed a metaverse-specific case study and analyzed it through the adversarial lens. Finally, we elaborate upon various open issues that require further research interest from the community.
arXiv comment24 pages, 11 figures
References in corpus (41)
- Distilling the Knowledge in a Neural Network
- Explaining and Harnessing Adversarial Examples
- Deep Learning with Differential Privacy
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- A Survey on Metaverse: Fundamentals, Security, and Privacy
- All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda
- Evasion Attacks against Machine Learning at Test Time
- Questioning the AI: Informing Design Practices for Explainable AI User Experiences
- Towards Deep Neural Network Architectures Robust to Adversarial Examples
- BAE: BERT-based Adversarial Examples for Text Classification
- A Survey on Metaverse: the State-of-the-art, Technologies, Applications, and Challenges
- Metaverse: Security and Privacy Issues
- Will Metaverse be NextG Internet? Vision, Hype, and Reality
- Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forward
- Security and Privacy Approaches in Mixed Reality: A Literature Survey
- Towards Transferable Adversarial Attack against Deep Face Recognition
- Applying Digital Twins in Metaverse: User Interface, Security and Privacy Challenges
- AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds
- Adversarial Training and Robustness for Multiple Perturbations
- On Physical Adversarial Patches for Object Detection
- Metaverse: Security and Privacy Concerns
- Artificial Intelligence for the Metaverse: A Survey
- Free-riders in Federated Learning: Attacks and Defenses
- BERT-ATTACK: Adversarial Attack Against BERT Using BERT
- A Full Dive into Realizing the Edge-enabled Metaverse: Visions, Enabling Technologies,and Challenges
- Adversarial Examples for Semantic Image Segmentation
- Security of Virtual Reality Authentication Methods in Metaverse: An Overview
- Data Driven Exploratory Attacks on Black Box Classifiers in Adversarial Domains
- Attack Trees for Security and Privacy in Social Virtual Reality Learning Environments
- QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks
- Transferable Adversarial Attacks for Image and Video Object Detection
- Life, the Metaverse and Everything: An Overview of Privacy, Ethics, and Governance in Metaverse
- The Threat of Adversarial Attacks on Machine Learning in Network Security -- A Survey
- When the Curious Abandon Honesty: Federated Learning Is Not Private
- MetaChain: A Novel Blockchain-based Framework for Metaverse Applications
- Hidden Backdoor Attack against Semantic Segmentation Models
- Human-Centered Explainable AI (XAI): From Algorithms to User Experiences
- HaS-Nets: A Heal and Select Mechanism to Defend DNNs Against Backdoor Attacks for Data Collection Scenarios
- SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters
- Dynamic Differential-Privacy Preserving SGD
- Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation