Music has always been extremely satisfying to listen to. My father’s audio cassette collection introduced me to classic hits from Queen, Bruce Springsteen, and Billy Joel along with a few Sanskrit strotams. Radio was quick to take over after I ran through the collection. But along with these songs came advertisements. Some were witty and most were annoying. For a regular listener, the witty ones soon get annoying. I soon moved to MP3s and then to streaming music. After I had purchased my first car, I decided to give the radio a listen again. The advertisements were still there, and I found myself skipping through stations for most of the drive. 14 years had gone by and almost nothing had changed. Except, that over the last decade, machine learning has become more accessible than it ever was. Could we use machine learning to classify an audio sample as either an advertisement or music? Definitely. The real question is how well can we perform this task?

Usually, when one thinks of encryption, they think of data being locked within a safe. You can transport this safe around but can only access it if you have the key. Information is secure this way. During my second summer during my graduate degree, I was introduced to Homomorphic Encryption – A new encryption scheme that not only kept information secure but allowed mathematical operations on data encrypted using HE. Information can not only be kept secure but transformed as well. This opens so many exciting avenues for the world of secure computing. If one wants to process sensitive data, a general concept would be to create a sandboxed environment with some network security. One could even set up an entirely offline environment. However, the world we live in is not so ideal. We have seen frequent data leaks and thefts. Both these solutions still have the data in plaintext and are just a barrier mechanism to prevent the transfer or access to data. With the boom in cloud infrastructure and the growing concerns of privacy, there is a need for a privacy-preserving solution.

Introduction

This project aims to scan real-life objects and generate its 3D model in virtual reality. Using a depth sensor, and circling the object of interest, we can generate a point cloud for a set of angles while the corresponding texture/color map. After some cleaning, the individual point clouds are stitched to create a 3D model. The last step would be to render a mesh over the obtained points. As a constraint, this project may be limited to scanning objects with simple geometrical shapes and using sensors at fixed locations. I did this project as a part of my Computational Geometery course taught by Dr. Renold Bailey.