collaborators

5 papers

cs.CR2026

Hidden Elo: Private Matchmaking through Encrypted Rating Systems

Mindaugas Budzys, Bin Liu, Antonis Michalas

Matchmaking has become a prevalent part in contemporary applications, being used in dating apps, social media, online games, contact tracing and in various other use-cases. However…

cs.LG2025

Oops!... They Stole it Again: Attacks on Split Learning

Tanveer Khan, Antonis Michalas

Split Learning (SL) is a collaborative learning approach that improves privacy by keeping data on the client-side while sharing only the intermediate output with a server. However,…

cs.CR2025

A Privacy-Centric Approach: Scalable and Secure Federated Learning Enabled by Hybrid Homomorphic Encryption

Khoa Nguyen, Tanveer Khan, Hossein Abdinasibfar +1

Federated Learning (FL) enables collaborative model training without sharing raw data, making it a promising approach for privacy-sensitive domains. Despite its potential, FL faces…

cs.LG2025

Split Happens: Combating Advanced Threats with Split Learning and Function Secret Sharing

Tanveer Khan, Mindaugas Budzys, Antonis Michalas

Split Learning (SL) -- splits a model into two distinct parts to help protect client data while enhancing Machine Learning (ML) processes. Though promising, SL has proven vulnerabl…

cs.LG2025

To Vaccinate or not to Vaccinate? Analyzing Power over the Pandemic

Tanveer Khan, Fahad Sohrab, Antonis Michalas +1

The COVID-19 pandemic has profoundly affected the normal course of life -- from lock-downs and virtual meetings to the unprecedentedly swift creation of vaccines. To halt the COVID…