Homomorphic learning: A privacy-focused approach to deep learning

Aadesh Neupane

CS601R Final Project

Homomorphic Learning

Basic Encryption Scheme

Encryption

Decryption

MNIST Example

MNIST Example

Encrypted MNIST

Encrypted Digit Usecase

Optical Recognition of Handwritten Digits Data Set

Sentiment Analysis

International Survey on Emotion Antecedents and Reactions (ISEAR)  dataset

joy -> "When I feel at peace with myself and also experience a close contact with people whom I regard greatly."

fear -> "Every time I imagine that someone I love or I could contact a serious illness, even death."

anger -> "When I had been obviously unjustly treated and had no possibility of elucidating this."

sadness -> "When I think about the short time that we live and relate it to the periods of my life when I think that I did not use this short time.",

disgust -> "At a gathering I found myself involuntarily sitting next to two people who expressed opinions that I considered very low and discriminating."

shame -> "When I realized that I was directing the feelings of discontent with myself at my partner and this way was trying to put the blame on him instead of sorting out my own feelings.",

guilt -> "I feel guilty when when I realize that I consider material things more important than caring for my relatives.  I feel very self-centered."

Sentiment Analysis

Simple RNN

Glove Embeddings

Simple CNN

BERT

Conclusion

  • Homomorphic Learning easy on image datasets

  • Hard to work with language data

Thank You!

CS601r

By Aadesh Neupane