Ph.D. candidate in Ingegneria Informatica E Dei Sistemi , 41st cycle (2025-2028)
Department of Control and Computer Engineering (DAUIN)
Profile
PhD
Research topic
AI4CTI - Artificial Intelligence for Cyber Threat Intelligence
Tutors
Keywords
Biography
Giovanni’s path to this research is rooted in rigorous academic evaluation. He earned his Master’s Degree in ICT for Smart Societies at PoliTO, followed by a research grant at the SmartData Center under Prof. Marco Mellia. There, he developed "Pcap-Encoder," culminating in a co-authored ACM SIGCOMM 2025 publication that critically debunked flawed LLM applications in network traffic classification.
Following a brief period applying generative AI to real-world cybersecurity in the industrial sector, Giovanni returned to academia to pursue his PhD. Today, he aims to build a new generation of reliable, AI-driven cyber defense tools that do not merely automate known playbooks but continuously discover, adapt, and evolve.
Research
Research groups
Publications
Latest publications View all publications in Porto@Iris
- Zhao, Yuqi; Dettori, Giovanni; Boffa, Matteo; Vassio, Luca; Mellia, Marco (2025)
The Sweet Danger of Sugar: Debunking Representation Learning for Encrypted Traffic Classification. In: SIGCOMM '25: ACM SIGCOMM 2025 Conference, Coimbra (PT), September 8 - 11, 2025, pp. 296-310. ISBN: 979-8-4007-1524-2
Contributo in Atti di Convegno (Proceeding)