Full Program

On Learning with Confidentiality through Encrypted AI Pipelines

Summary:

In the current technological ecosystem driven by advancements in Artificial Intelligence (AI) and Machine Learning (ML) there is an articulated demand for secure data (DataOps) and learning (AIOps or MLOps) operations. The compromise of sensitive data may provoke irreparable harm to both individuals and organizations. There is a critical need to adhere to various constraints designed to securely process and analyze sensitive data without revealing any pertinent information. This work introduces the Private AI/ML Operations Flow which develops a framework able to perform descriptive and predictive analytics with confidentiality. The framework utilizes Fully Homomorphic Encryption (FHE) and Order Revealing Encryption (ORE) schemes to encrypt data and trains AI/ML algorithms to learn patterns with privacy. By enabling AI/ML algorithms to be trained directly on encrypted data the framework allows for the discovery of valuable insights without ever revealing the underlying sensitive information preserving the confidentiality of the learnt patterns.

Author(s):

Theodora Anastasiou    
UBITECH LTD
Cyprus

Machine Learning Research Associate at UBITECH, specializing in AI research and adversarial machine learning, with a focus on developing robust, secure, and explainable AI/ML systems. Holding a BSc and MSc in Informatics and Telecommunications, alongside an ongoing MBA, with expertise in programming, data science, and web development. Experienced in designing and implementing AI models, optimizing machine learning pipelines, and ensuring system security and interpretability.

Stavroula Iatropoulou    
UBITECH LTD
Cyprus

As a Software Engineer in UBITECH, I work on designing, developing, and deploying software solutions. My skills in programming languages (Java, Python) help to create web applications and services that utilize data analysis methods and machine learning techniques. I also collaborate with other engineers and researchers to deliver high-quality products and services to clients and partners.

I have an academic background in computer science with a Bachelor's degree from the Department of Informatics and Telecommunications of the National and Kapodistrian University of Athens, in July 2020. My thesis on "Fake News Detection in News Articles Using Machine and Deep Learning Methods" was implemented with Natural Language Processing methods and Neural Networks. I am currently pursuing a master's degree entitled "Digital Technologies and Smart Infrastructures in Agriculture" at the Agricultural University of Athens and is working on her thesis on "Remote sensing techniques for detecting water and nutrient deficiency in the plant Valerianella locusta grown in a closed hydroponic vertical cultivation system using a multispectral camera."

Sophia Karagiorgou    
UBITECH LTD
Cyprus

An experienced senior Research and Innovation (R&I) manager, also serving on the Board of Directors (BoD) at Adra and leading the Data and AI/ML Systems (DAI) department of UBITECH. She possesses expertise in Process Modelling, Service-Oriented Architecture (SOA), High-performance Data Analytics (HPDA) and various programming languages such as Python, JAVA, C/C++, and C#. Proficient in the domains of Big Data, Artificial Intelligence, Computer Science, and Databases, accompanied by a scholarly record exceeding 40 publications.