Skip to content
Francesco Marchiori

Data Scientist · AI & Cybersecurity

Francesco Marchiori

Data Scientist @ Negentro

I am a Data Scientist at Negentro and a PhD graduate in Brain, Mind and Computer Science (BMCS) from the University of Padua.

About

I am a Data Scientist at Negentro and a PhD graduate in Brain, Mind and Computer Science (BMCS) from the University of Padua.

My research focuses on:

  • Artificial Intelligence
  • Machine Learning & Deep Learning
  • Security & Privacy
  • Adversarial Attacks
  • Cyber Threat Intelligence
  • Quantum Cryptography & Computing

During my PhD, I was part of the SPRITZ – Security and Privacy Research Group, supervised by Prof. Mauro Conti. My research explored the intersection between AI and cybersecurity, particularly in automotive cyber-physical systems.

Experience

Data Scientist

· Negentro

Oct 2025 – Present | Milan, Italy (Remote)

  • Development of an AI-driven platform for the startup

Visiting Researcher

· Stanford University

Jan 2025 – Apr 2025 | Stanford, CA, USA

  • Research on security of Large Language Models (LLMs) and Vision-Language Models (VLMs)
  • Development of a novel jailbreaking detection system

Visiting Researcher

· University of Luxembourg

Sept 2024 | Luxembourg, Luxembourg

  • Research on Android Auto/Automotive OS location inference attacks
  • Discovery, analysis, and submission of permission bypass vulnerability to Google

Cyber Threat Intelligence Intern

· Leonardo S.p.A.

Mar 2022 – Jun 2022 | Rome, Italy (Hybrid)

  • Research on Cyber Threat Intelligence, NLP and Deep Learning
  • Development of STIXnet, an entity & relation extraction platform for CTI reports

Education

PhD in Brain, Mind and Computer Science

University of Padova

Oct 2022 – Sept 2025 | Padova, Italy

Grade
With Honors (Cum Laude)
Thesis
Cybersecurity and AI in Automotive Cyber-Physical Systems
Supervisor
Prof. Mauro Conti

MSc in Cybersecurity

University of Padova

Oct 2020 – Oct 2022 | Padova, Italy

Grade
110/110
Thesis
STIXnet: Entity and Relation Extraction from Unstructured CTI Reports
Supervisor
Prof. Mauro Conti

BSc in Information Engineering

University of Padova

Oct 2017 – Oct 2020 | Padova, Italy

Grade
96/110
Thesis
Quantum Teleportation
Supervisor
Prof. Roberto Corvaja

Teaching

Advanced Topics in Computer and Network Security

· Teaching Assistant

University of Padova

Oct 2022 – Sept 2025

  • Advanced security concepts
  • Analysis of state-of-the-art research in cybersecurity

Ethical Hacking

· Teaching Assistant

University of Padova

Oct 2022 – Sept 2025

  • Ethical hacking methodologies
  • Offensive security tools and techniques
  • Systematic analysis of cyber-attack methodologies

Awards

  • IEEE LCN 2024 Student Travel Grant
  • Erasmus+ PhD Mobility Grant (University of Luxembourg)
  • 2023 Thesis Award “Pierluigi Manzoni”
  • Best Research Paper Award Runner-Up — ARES 2023

Academic service

Program Committee

ACSW 2025 · AI&CCPS 2025 · AIMS 2025 · EuroS&P 2025 · WAITI 2024 · WEB-for-GOOD 2024 · WISE 2024

Reviewing

Computers & Security · ESORICS 2024 · EuroS&P 2023 · Intelligent Systems · Knowledge-Based Systems

Session Chair

WiseML 2024

Featured publications

See all publications
Conference2025

DUMB and DUMBer: Is Adversarial Training Worth It in the Real World?

Francesco Marchiori, Marco Alecci, Luca Pajola, Mauro Conti

30th European Symposium on Research in Computer Security (ESORICS 2025)

Conference2025

Leaky Batteries: A Novel Set of Side-Channel Attacks on Electric Vehicles

Francesco Marchiori, Mauro Conti

20th International Conference on Availability, Reliability and Security (ARES 2025)

Conference2024

CANEDERLI: On The Impact of Adversarial Training and Transferability on CAN Intrusion Detection Systems

Francesco Marchiori, Mauro Conti

Proceedings of the 2024 ACM Workshop on Wireless Security and Machine Learning (WiseML 2024) · Seoul, Republic of Korea

Conference2023

Your Battery Is a Blast! Safeguarding Against Counterfeit Batteries with Authentication

Francesco Marchiori, Mauro Conti

Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security (CCS 2023) · Copenhagen, Denmark

Blog

Open blog

PhDone: 3 years in numbers

A short reflection after defending my PhD, and why I started tracking the in-between parts of the process.

Contact

Open to collaborations in AI security, adversarial ML, and applied research projects.