Towards Safer Augmented Reality: Identifying, Evaluating, and Mitigating Security & Privacy Threats

Subscribers:
342,000
Published on ● Video Link: https://www.youtube.com/watch?v=mIUrCJdi2Lo



Duration: 0:00
296 views
7


Augmented-reality (AR) technologies merge virtual content with users' perceptions of the real-world environment. These technologies revolutionize how humans interact with the surrounding world, and enhance machine understanding of human behavior and physical spaces. As AR devices become increasingly available, protecting users from inherent security and privacy risks becomes even more imperative. In this talk, I will present our approach for identifying and evaluating these risks in today's AR system. First, we adopt a user-centric analysis to explore privacy challenges by examining how users understand and feel about eye-tracking and hand-tracking permissions in AR devices. Next, we evaluate the security of current AR platforms by identifying key three-dimensional user interface (3D UI) security properties and demonstrating the implications of various instantiations of these properties on ARCore (Google), ARKit (Apple), HoloLens (Microsoft), Oculus (Meta), and WebXR (browser). Finally, I will conclude with ongoing work developing mitigation solutions to enhance user safety, with directions for future work.




Other Videos By Microsoft Research


6 days agoMicrosoft as Customer Zero: Empowering Research Teams with AI
6 days agoA Fever Dream of Machine Learning Framework Composability
2025-04-29AI for Africa’s Future: Innovation, Equity, and Impact
2025-04-22Hamming Quasi-Cyclic
2025-04-22Towards Safer Augmented Reality: Identifying, Evaluating, and Mitigating Security & Privacy Threats
2025-04-22Shining light on the learning brain: Estimating mental workload in a simulated flight task using opt
2025-03-24How to Compress Garbled Circuit Input Labels, Efficiently
2025-03-24Differentially Private Synthetic Data without Training
2025-03-21Celebrating Susan Dumais: Reflections on a Legacy of Research and Collaboration | Plenary Session
2025-03-21The Assistant: Situated Interaction Project (2012)
2025-03-20The AI Revolution in Medicine, Revisited: An Introduction
2025-03-10AI and Europe's history of reinvention
2025-03-03World and Human Action Models towards gameplay ideation (Supplementary Video 1)
2025-03-03LLMs vs. Torch 1.5: Why Your Code Assistant Can't Keep Up
2025-02-25Using LLMs for safe low-level programming | Microsoft Research Forum
2025-02-25AutoGen v0.4: Reimagining the foundation of agentic AI for scale and more | Microsoft Research Forum
2025-02-25Belief state transformers | Microsoft Research Forum
2025-02-25Magma: A foundation model for multimodal AI Agents | Microsoft Research Forum
2025-02-25Chimera: Accurate synthesis prediction by ensembling models with... | Microsoft Research Forum
2025-02-25AI for Precision Health: Learning the language of nature and patients | Microsoft Research Forum
2025-02-25Keynote: Multimodal Generative AI for Precision Health | Microsoft Research Forum