• Corpus ID: 215814503

Conservative Plane Releasing for Spatial Privacy Protection in Mixed Reality

@article{Guzman2020ConservativePR,
  title={Conservative Plane Releasing for Spatial Privacy Protection in Mixed Reality},
  author={Jaybie A. de Guzman and Kanchana Thilakarathna and Aruna Prasad Seneviratne},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.08029}
}
Augmented reality (AR) or mixed reality (MR) platforms require spatial understanding to detect objects or surfaces, often including their structural (i.e. spatial geometry) and photometric (e.g. color, and texture) attributes, to allow applications to place virtual or synthetic objects seemingly "anchored" on to real world objects; in some cases, even allowing interactions between the physical and virtual objects. These functionalities require AR/MR platforms to capture the 3D spatial… 

User configurable 3D object regeneration for spatial privacy

TLDR
This work uses an existing adversarial autoencoder to generate copies of 3D objects where the likeness of the copies from the original can be varied, and shows that the proposed privacy framework can indeed variably effect the privacy of a 3D object by varying the privilege level.

Unravelling Spatial Privacy Risks of Mobile Mixed Reality Data

TLDR
This work analyzes MR spatial data using various spatial complexity metrics---including a cosine similarity-based, and a Euclidean distance-based metric---as heuristic or empirical measures that can signify the inference risk a captured space has.

Let’s SOUP up XR: Collected thoughts from an IEEE VR workshop on privacy in mixed reality

This paper presents insights from the PrXR workshop conducted at IEEE VR 2021. We identified several topic areas related to privacy and security risks for virtual, augmented, and mixed-reality (XR)

References

SHOWING 1-10 OF 41 REFERENCES

A First Look into Privacy Leakage in 3D Mixed Reality Data

TLDR
This work reveals the privacy leakage from released 3D MR data and how the leakage persist even after implementing spatial generalizations and abstractions, and formalizes the spatial privacy problem in 3D mixed reality data as well as the adversary model.

Privacy Preserving Image-Based Localization

TLDR
The key idea of the approach is to lift the map representation from a 3D point cloud to a3D line cloud, which obfuscates the underlying scene geometry while providing sufficient geometric constraints to enable robust and accurate 6-DOF camera pose estimation.

SafeMR: Privacy-aware Visual Information Protection for Mobile Mixed Reality

TLDR
This work presents a visual access control mechanism in the form of object-level abstraction for fine-grained access control in a mobile device and shows reduction in execution times from visual processing resource sharing is another consequential benefit of abstraction without any energy consumption impact.

Security and Privacy Approaches in Mixed Reality

TLDR
The scope is extended to include work on related technologies such as augmented reality, virtual reality, and human-computer interaction as crucial components, if not the origins, of MR, as well as numerous related work from the larger area of mobile devices, wearables, and Internet ofThings.

Least Privilege Rendering in a 3D Web Browser

TLDR
This work introduces two new abstractions enabling least privilege interactions of apps with the room, and builds SurroundWeb, a 3D browser that enables web applications to use object recognition and room display capabilities with the authors' least privilege abstractions.

I-Pic: A Platform for Privacy-Compliant Image Capture

TLDR
I-Pic, a trusted software platform that integrates digital capture with user-defined privacy, shows that a practical, energy-efficient system that conforms to the privacy choices of many users within a scene can be built and deployed using current hardware.

Enabling Fine-Grained Permissions for Augmented Reality Applications with Recognizers

TLDR
This work proposes a fine-grained permission system where applications request permissions at the granularity of recognizer objects, and builds a prototype on Windows that exposes nine recognizers to applications, including the Kinect skeleton tracker.

SurroundWeb: Mitigating Privacy Concerns in a 3D Web Browser

TLDR
Surround Web is presented, the first 3D web browser, which provides the novel functionality of rendering web content onto a room while tackling many of the inherent privacy challenges.

A context-based privacy preserving framework for wearable visual lifeloggers

TLDR
A novel efficient privacy-aware framework for wearable cameras that can protect all sensitive subjects such as people, objects and locations and uses the contextual information obtained from the wearable's sensors and recorded images to identify the potential sensitive subjects in each image.

Revealing Scenes by Inverting Structure From Motion Reconstructions

TLDR
It is shown, for the first time, that 3D point clouds retain enough information to reveal scene appearance and compromise privacy, and a privacy attack that reconstructs color images of the scene from the point cloud is presented.