Lorenzo Guerra

Lorenzo Guerra

PhD Researcher in ML for Cybersecurity

Paris, France

I'm a PhD Candidate at Telecom Paris (Institut Polytechnique de Paris), conducting my research in partnership with Renault Group through a CIFRE fellowship. My work focuses on self-supervised and graph-based learning for intrusion detection in distributed real-time systems, including software-defined vehicles.

I am particularly interested in model design for robust, deployable intrusion detection systems, with evaluation and online adaptation after detection as complementary directions. I'm also a retired CTF player and took part in the national finals of CyberChallenge.IT.

Publications

How Benchmarks and Evaluation Protocols Shape Conclusions in Provenance-Based Intrusion Detection

Lorenzo Guerra, Thomas Chapuis, Guillaume Duc, Pavlo Mozharovskyi, Van-Tam Nguyen

Network and Distributed System Security Symposium (NDSS), 2027

Paper Code

Self-Supervised Learning of Graph Representations for Network Intrusion Detection

Lorenzo Guerra, Thomas Chapuis, Guillaume Duc, Pavlo Mozharovskyi, Van-Tam Nguyen

Advances in Neural Information Processing Systems 38 (NeurIPS), 2025

Paper Code

AI-Driven Intrusion Detection Systems (IDS) on the ROAD Dataset: A Comparative Analysis for Automotive Controller Area Network (CAN)

Lorenzo Guerra, Linhan Xu, Paolo Bellavista, Thomas Chapuis, Guillaume Duc, Pavlo Mozharovskyi, Van-Tam Nguyen

1st Cyber Security in Cars Workshop (CSCS) at the 31st ACM Conference on Computer and Communications Security (CCS), 2024

Paper Code

Experience & Education

Industrial PhD Researcher
Telecom Paris (IP Paris) & Renault Group Mar 2024 - Present
Industrial PhD focused on applied machine learning for cybersecurity. Developed graph- and sequence-based methods for intrusion and anomaly detection across network, host, and in-vehicle telemetry, and led research on benchmark design and evaluation protocols for intrusion detection systems.
Research Intern
Telecom Paris (IP Paris) June 2023 - Dec 2023
Researching ML powered intrusion detection systems for automotive applications. Analysis of CAN security and applied state-of-the-art ML models on intrusion detection datasets.
National Finals Participant
CyberChallenge.IT Jan 2022 - Jul 2022
Completed a six-month cybersecurity training program, placed 2nd locally, and represented the University of Bologna at the national finals.
M.Sc. Computer Engineering
University of Bologna 2021 - 2024
Cybersecurity & ML focus - Erasmus at Sorbonne Universite
B.Sc. Computer Engineering
University of Bologna 2018 - 2021