Hello, I'm

Dr. Luca
Di Grazia

Great Minds Fellow at the University of St. Gallen in Switzerland, working at the intersection of Artificial Intelligence, Software Security, and Technology Innovation.

About Me

Research Interests

Artificial Intelligence Cybersecurity Software Verification Vibe Coding


Luca Di Grazia holds a Great Minds Fellowship ($230,000) at the University of St. Gallen in Switzerland, focusing on the security of AI-generated code, hosted by Prof. Dr. Guido Salvaneschi. Previously, he was a Postdoctoral Researcher at USI Lugano, working on GenAI for software testing and verification under Prof. Dr. Mauro Pezzè.

He earned his Ph.D. in Computer Science (summa cum laude) from the University of Stuttgart, supervised by Prof. Dr. Michael Pradel. His dissertation explored innovative approaches to software maintenance through search and predictions.

During a Research Internship at Uber in Amsterdam, he developed a GenAI-based bug-fixing approach that won an internal competition against 103 teams, with results presented directly to the Uber CEO.

His research interests are on Security of AI Agents (FSE 2026), Generative AI to automatically generate tests (ICSE 2026 and ASE 2025), Python type errors (ASE 2026, ICSE 2024 and FSE 2022, Distinguished Paper Award), and more.

Career Path

  1. University of St. Gallen
    2025 – Present

    Great Minds Fellow

    University of St. Gallen, Switzerland

  2. USI Lugano
    2024 – 2025

    Postdoctoral Researcher

    USI Lugano, Switzerland

  3. Uber
    2023

    Research Intern in Generative AI

    Uber, Amsterdam, Netherlands

  4. University of Stuttgart
    2019 – 2024

    Ph.D. in Computer Science (summa cum laude)

    University of Stuttgart, Germany

  5. Politecnico di Torino
    2013 – 2019

    B.Sc. & M.Sc. in Computer Engineering

    Politecnico di Torino, Italy

Key Achievements

Funding

Great Minds Fellowship

Secured 189,747 CHF ($230,000) in competitive research funding as Principal Investigator through the Great Minds Fellowship (Universität St.Gallen) for the project Secure Software in the Age of Massively GenAI-Generated Code.

Industry

Uber GenAI Competition

Won Uber's 2023 GenAI Competition in Amsterdam for using Generative AI to improve developer productivity in bug fixing, outperforming 103 teams and presenting the results to Uber's CEO and Executive Leadership Team.

Academia

Top-tier publications

Published at all A* flagship software engineering conferences in the same year (ICSE'26, FSE'26, ASE'26) with three independent research groups; recipient of a ACM SIGSOFT Distinguished Paper Award (FSE'22).

Peer-Reviewed Publications

Journal Ranking: Q1

Reconstructing Objects for Software Testing

Qiu, K.; Di Grazia, L.; Gambi, A.; Fazzini, M.; Pezzè, M.

LLMs turn objects captured in production into readable Java test code.

Conference Ranking: CORE A*

All or Nothing: How Library Type Annotations Affect Client-Side Errors in Python

Asare, E.; Di Grazia, L.; Nadi, S.

Python type checking pays off only when the libraries you use are fully annotated.

Conference Ranking: CORE A*

AgentBound: Securing Execution Boundaries of AI Agents

Bühler, C.; Biagiola, M.; Di Grazia, L.; Salvaneschi, G.

The first access control framework for MCP servers, stopping malicious AI agents.

Conference Ranking: CORE A*

E-Test: E'er-Improving Test Suites

Qiu, K.; Di Grazia, L.; Mariani, L.; Pezzè, M.

LLMs find the scenarios your tests miss and add tests for them.

Conference Ranking: CORE A*

Do LLMs Generate Useful Concrete Test Oracles?

Molinelli, D.; Di Grazia, L.; Lopez, A.; Ernst, M.; Pezzè, M.

How well LLMs write test oracles, measured on 13,866 oracles from 135 Java projects.

Journal Ranking: Q1

From Today's Code to Tomorrow's Symphony: The AI Transformation of Developer's Routine by 2030

Qiu, K.; Puccinelli, N.; Ciniselli, M.; Di Grazia, L.

HyperAssistant: how AI will change developers' daily work by 2030.

Conference Ranking: CORE A*

PyTy: Repairing Static Type Errors in Python

Chow, Y.; Di Grazia, L.; Pradel, M.

Automatically fixes 85.4% of static type errors in Python code.

Conference Ranking: CORE A

The Fault in Our Stars: Reproducible Large-scale Code Analysis

Maj, P.; Muroya, S.; Siek, K.; Di Grazia, L.; Vitek, J.

How to sample software repositories for reproducible large-scale studies.

Journal Ranking: Q1

Code Search: A Survey of Techniques for Finding Code

Di Grazia, L.; Pradel, M.

30 years of code search research: queries, indexing, retrieval and ranking.

Journal Ranking: Q1

DiffSearch: A Scalable Search Engine for Code Changes

Di Grazia, L.; Bredl, P.; Pradel, M.

A search engine that finds code changes among millions in seconds.

Conference Ranking: CORE A*

The Evolution of Type Annotations in Python

Di Grazia, L.; Pradel, M.
🏆 ACM SIGSOFT Distinguished Paper Award

How developers use type annotations: 1.4M changes in 9,655 Python repositories.

BibTeX


        

Get in Touch

Address

Torstrasse 25
9000 St. Gallen
Switzerland

Institutional Email

luca.digrazia@unisg.ch

Private Email

work@lucadigrazia.com

LinkedIn GitHub Google Scholar ORCID DBLP