Machine Learning (ML) has emerged as one of data science's most transformative and influential domains. However, the widespread adoption of ML introduces privacy-related concerns owing to the increasing number of malicious attacks targeting ML models. To address these concerns, Privacy-Preserving Machine Learning (PPML) methods have been introduced to safeguard the privacy and security of ML models. One such approach is the use of Homomorphic Encryption (HE). However, the significant drawbacks and inefficiencies of traditional HE render it impractical for highly scalable scenarios. Fortunately, a modern cryptographic scheme, Hybrid Homomorphic Encryption (HHE), has recently emerged, combining the strengths of symmetric cryptography and HE to surmount these challenges. Our work seeks to introduce HHE to ML by designing a PPML scheme tailored for end devices. We leverage HHE as the fundamental building block to enable secure learning of classification outcomes over encrypted data, all while preserving the privacy of the input data and ML model. We demonstrate the real-world applicability of our construction by developing and evaluating an HHE-based PPML application for classifying heart disease based on sensitive ECG data. Notably, our evaluations revealed a slight reduction in accuracy compared to inference on plaintext data. Additionally, both the analyst and end devices experience minimal communication and computation costs, underscoring the practical viability of our approach. The successful integration of HHE into PPML provides a glimpse into a more secure and privacy-conscious future for machine learning on relatively constrained end devices.

Over the past few years, a tremendous growth of machine learning was brought about by a significant increase in adoption of cloud-based services. As a result, various solutions have been proposed in which the machine learning models run on a remote cloud provider. However, when such a model is deployed on an untrusted cloud, it is of vital importance that the users' privacy is preserved. To this end, we propose Blind Faith -- a machine learning model in which the training phase occurs in plaintext data, but the classification of the users' inputs is performed on homomorphically encrypted ciphertexts. To make our construction compatible with homomorphic encryption, we approximate the activation functions using Chebyshev polynomials. This allowed us to build a privacy-preserving machine learning model that can classify encrypted images. Blind Faith preserves users' privacy since it can perform high accuracy predictions by performing computations directly on encrypted data.

Split Learning (SL) is a new collaborative learning technique that allows participants, e.g. a client and a server, to train machine learning models without the client sharing raw data. In this setting, the client initially applies its part of the machine learning model on the raw data to generate activation maps and then sends them to the server to continue the training process. Previous works in the field demonstrated that reconstructing activation maps could result in privacy leakage of client data. In addition to that, existing mitigation techniques that overcome the privacy leakage of SL prove to be significantly worse in terms of accuracy. In this paper, we improve upon previous works by constructing a protocol based on U-shaped SL that can operate on homomorphically encrypted data. More precisely, in our approach, the client applies Homomorphic Encryption (HE) on the activation maps before sending them to the server, thus protecting user privacy. This is an important improvement that reduces privacy leakage in comparison to other SL-based works. Finally, our results show that, with the optimum set of parameters, training with HE data in the U-shaped SL setting only reduces accuracy by 2.65% compared to training on plaintext. In addition, raw training data privacy is preserved.

Machine learning methods are widely used for a variety of prediction problems. \emph{Prediction as a service} is a paradigm in which service providers with technological expertise and computational resources may perform predictions for clients. However, data privacy severely restricts the applicability of such services, unless measures to keep client data private (even from the service provider) are designed. Equally important is to minimize the amount of computation and communication required between client and server. Fully homomorphic encryption offers a possible way out, whereby clients may encrypt their data, and on which the server may perform arithmetic computations. The main drawback of using fully homomorphic encryption is the amount of time required to evaluate large machine learning models on encrypted data. We combine ideas from the machine learning literature, particularly work on binarization and sparsification of neural networks, together with algorithmic tools to speed-up and parallelize computation using encrypted data.

Machine Learning (ML), addresses a multitude of complex issues in multiple disciplines, including social sciences, finance, and medical research. ML models require substantial computing power and are only as powerful as the data utilized. Due to high computational cost of ML methods, data scientists frequently use Machine Learning-as-a-Service (MLaaS) to outsource computation to external servers. However, when working with private information, like financial data or health records, outsourcing the computation might result in privacy issues. Recent advances in Privacy-Preserving Techniques (PPTs) have enabled ML training and inference over protected data through the use of Privacy-Preserving Machine Learning (PPML). However, these techniques are still at a preliminary stage and their application in real-world situations is demanding. In order to comprehend discrepancy between theoretical research suggestions and actual applications, this work examines the past and present of PPML, focusing on Homomorphic Encryption (HE) and Secure Multi-party Computation (SMPC) applied to ML. This work primarily focuses on the ML model's training phase, where maintaining user data privacy is of utmost importance. We provide a solid theoretical background that eases the understanding of current approaches and their limitations. In addition, we present a SoK of the most recent PPML frameworks for model training and provide a comprehensive comparison in terms of the unique properties and performances on standard benchmarks. Also, we reproduce the results for some of the papers and examine at what level existing works in the field provide support for open science. We believe our work serves as a valuable contribution by raising awareness about the current gap between theoretical advancements and real-world applications in PPML, specifically regarding open-source availability, reproducibility, and usability.