Changes between Version 35 and Version 36 of Other/Summer/2024/pLS
- Timestamp:
- Aug 7, 2024, 1:37:12 PM (4 months ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Other/Summer/2024/pLS
v35 v36 14 14 <a href=style="color:#BB0000;">Emily Yao</a><sup>HS</sup> 15 15 </p> 16 <p><span style="color:#BB0000; font-weight: bold;"><a href="https:// google.com">Final Poster</a>16 <p><span style="color:#BB0000; font-weight: bold;"><a href="https://docs.google.com/presentation/d/1-DTirqw1xlwxzQvLg-a_ucX3ex9LzDbn/edit#slide=id.g2ef813b4c52_1_29">Final Poster</a> 17 17 </span> 18 18 … … 20 20 21 21 == Project Overview 22 Augmented reality/virtual reality (AR/VR) is used for many applications and have been used for many purposes ranging from communicating and tourism, all the way to healthcare. Accessing the built-in motion sensors does not require user permissions, as most VR applications need to access this information in order to function. However, this introduces the possibility of privacy vulnerabilities: zero-permission motion sensors can be used in order to infer live speech, which is a problem when that speech may include sensitive information.22 Augmented reality/virtual reality (AR/VR) is used for many applications and have been used for many purposes ranging from communicating and tourism, all the way to healthcare. Accessing the built-in motion sensors does not require user permissions, as most VR applications need to access this information in order to function. However, this introduces the possibility of privacy vulnerabilities: data from zero-permission motion sensors encodes various types of the user’s private information, such as activity information and preferences. 23 23 24 24 == Project Goal 25 The purpose of this project is to extract motion data from AR/VR devices inertial measurement unit (IMU), and then input this data to a large language model (LLM) to predict what the user is doing 25 * Investigate privacy leakage in AR/VR devices 26 * Extract data from the IMU on AR/VR headset and controllers for Human Activity Recognition (HAR) 27 * Use Support Vector Machine (SVM) and Large Language Model (LLM) to show how IMU data maliciously exposes activities of victim users 26 28 27 29 == Weekly Updates … … 237 239 238 240 <a 239 href="https:// google.com" style="color:#BB0000; margin-right: 20px;">Week 10241 href="https://docs.google.com/presentation/d/1Ikq0lZkyyXrQlckJNZyvSo3K0u711e0oNYIOngolotU/edit" style="color:#BB0000; margin-right: 20px;">Week 10 240 242 </a> 241 243 242 244 <a 243 href="https:// google.com" style="color:#BB0000; margin-right: 20px;">Final Presentation245 href="https://docs.google.com/presentation/d/1WhneLK6GSfdTVr_OQ9CEG0FSX2G0BvsY/edit#slide=id.p1" style="color:#BB0000; margin-right: 20px;">Final Presentation 244 246 </a> 245 247