Giulio Segalini

Neuchâtel, Switzerland

I am a PhD candidate at the University of Neuchâtel. My work focuses on AI privacy and security, especially in agentic or generative systems, privacy-preserving computation, and secure distributed/federated systems.

Before starting my PhD, I completed a cum laude M.Sc. in Computer Science through the 4TU Cybersecurity program at Delft University of Technology. I also worked as a (head) teaching assistant for various courses including Network Security, Operating Systems, Computer Security, and Distributed Algorithms.

This site collects my selected publications, research and software projects, and CV.

selected publications

Middleware
Byzantine-Resilient Federated Computation of Differentially Private Summary Statistics

Giulio Segalini, Maria Fernandes, and Jérémie Decouchant

In Middleware 2025 - Proceedings of the 26th ACM International Middleware Conference, 2025

Abs DOI Bib

Summary statistics are essential to analyse large datasets in various fields, including financial and medical research. Federated computations enhance statistical power by combining geo-distributed datasets while ensuring compliance with data protection regulations, privacy guarantees, and resilience against intrusions. We present Tides, a federated framework leveraging Trusted Execution Environments (TEEs) to defend against adversaries controlling up to f of the N datacenters. We present an instantiation of Tides using genomic (GWAS) statistics. We address TEE-specific attack vectors, including communication blocking and side-channel attacks. Tides follows three key steps: TEEs share statistical results through reliable broadcast and run randomized crash-tolerant binary consensus to identify available datasets; TEEs enforce differential privacy with ad hoc noise; and TEEs run memory-oblivious algorithms to compute the final summary statistics. We implemented Tides with Intel SGX enclaves and demonstrated its practicality with three datasets.
@inproceedings{segalini2025byzantine, title = {Byzantine-Resilient Federated Computation of Differentially Private Summary Statistics}, author = {Segalini, Giulio and Fernandes, Maria and Decouchant, J{\'e}r{\'e}mie}, booktitle = {Middleware 2025 - Proceedings of the 26th ACM International Middleware Conference}, publisher = {Association for Computing Machinery}, pages = {72--85}, year = {2025}, doi = {10.1145/3721462.3770766}, }