Antonio Scardace
|
“Stay hungry, stay foolish.”
SCROLL DOWN
SWIPE UP
About me
I am 25 years old. In July 2025, I graduated with honours in a Master’s degree in Computer Science from the University of Catania, earning a final grade of 110/110 with honors. I had previously completed my Bachelor’s degree in March 2023, also with top grade and honours. On both occasions, I was nominated for a prestigious merit prize, recognizing exceptional students in my department.
I have conducted research activities for over three years focusing on String Matching Algorithms and Quantum Computing under Professor Simone Faro.
Since September 2024, I have been conducting research in Medical Imaging under Professor Daniele Ravì. In October 2025, I began my PhD in Computer Science under his supervision, focusing on multimodal AI for healthcare. My first research interest is to model a multimodal brain connectome for Disease Progression Modeling in neurodegenerative disorders such as Alzheimer’s. Another research interest of mine focuses on detecting and quantifying memorization in generative models.
In September 2020, I was also selected as a mentee for LeadTheFuture, a Forbes-awarded mentorship organization for talented Italian students with <13% acceptance rate. Recently, in May 2023, I was honoured to become an Ambassador for the organization.
LeadTheFuture has shown me the incredible impact of surrounding myself with the right people on my personal growth. I am eager to connect with visionary mentors and peers. With a strong devotion to Computer Science and the Public Interest, I aim to merge these fields to achieve meaningful social impact. In particular, I am fascinated by the application of AI in Healthcare to improve lives, and beyond innovation, I want to help Italy counteract brain drain.
Publications
A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis
IEEE/CVF Winter Conference on Applications of Computer Vision 2026 (WACV) • openaccess.thecvf.com
In this paper, we address the risk of patient data leakage in deep generative models for medical imaging, which may memorize sensitive training samples. We propose DeepSSIM, a self-supervised metric designed to detect and quantify memorization across large sets of generated images, providing a scalable solution to safeguard privacy.
Practical Implementation of a Quantum String Matching Algorithm
Association for Computing Machinery (QUASAR'24) • doi.org/10.1145/3660318.3660327
This paper presents a first practical implementation of a quantum circuit tailored to address string matching, particularly focusing on binary strings. By elucidating various algorithmic nuances overlooked in prior theoretical formulations, our solution serves as a conduit between the realms of text processing and quantum computing, fostering cross-disciplinary dialogue and innovation.
The Great Textual Hoax: Boosting Sampled String Matching with Fake Samples
12th International Conference on Fun with Algorithms (FUN 2024) • doi.org/10.4230/LIPIcs.FUN.2024.13
This paper explores character distance sampling, a cutting-edge text sampling technique focusing on sampling distances between characters in a selected alphabet. We propose the introduction of strategically placed fake samples, which significantly reduce the required index space by nearly 50% without compromising the algorithm's correctness. This method also enhances the algorithm’s efficiency under specific conditions.
Towards an Efficient Text Sampling Approach for Exact and Approximate Matching
Prague Stringology Conference 2021 (PSC 2021) • stringology.org/event/2021/p07
In this paper we present some preliminary results obtained in the attempt to extend sampled-string matching to the general case of approximate string matching. Specifically, we introduce a new sampling approach which turns out to be suitable for both exact and approximate matching and evaluate it in the context of a specific case of approximate matching, the order preserving pattern matching problem.