Protocol Labs Research

Irene Giacomelli

Research Scientist / CryptoNetLab


PhD in Cryptography, 2016

Aarhus University

MSc in Mathematics, 2012

University of Pisa

BS in Mathematics, 2009

University of Pisa

Irene is an Italian cryptographer based in Switzerland. She completed her Ph.D. at Aarhus University (Denmark) in 2016 after her undergraduate studies in Mathematics at Pisa University (Italy). After completing her Ph.D., she was a research assistant (postdoc), first in the USA (Madison, WI) and then in Italy (ISI Foundation, Turin). Her postdoctoral work focused on privacy-preserving machine-learning. Her research interests lie in the area of cryptographic protocol design and in the intersections between cryptography and other fields such machine-learning and blockchain technology.

Areas of Expertise


Latest work

2020.11.23 / Posts

A Research Perspective on Filecoin, Part Two

In Part One, we traced the intellectual and technological history of modern implementations of distributed ledger technology. Now let’s take a stroll through the technological landscape around the time of Filecoin’s release:

2020.11.16 / Posts

A Research Perspective on Filecoin

The Filecoin network is launching in the middle of a revolution in internet architecture, where vulnerable centralized services dependent on trusted parties are being replaced with resilient decentralized solutions based on verifiable computation, and internet services are being relocated from inefficient central monoliths to the far reaches of the network by peer-to-peer markets.

2020.4.8 / Publications

MonZa: Fast maliciously secure two party computation on Z_{2^k}

In this paper we present a new 2-party protocol for secure computation over rings of the form Z2k. As many recent efficient MPC protocols supporting dishonest majority, our protocol consists of a heavier (input-independent) pre-processing phase and a very efficient online stage.

2019.11.20 / Publications

Exploring connections between active learning and model extraction

Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the model, and (b) a user-friendly query interface to access the model.