Generative AI for synthetic traffic
Generative AI models that produce realistic and privacy-preserving synthetic traffic, to augment datasets and train traffic classifiers.
Tools & projects
People
Antonio PescapèFull Professor · Principal Investigator
Alfredo NascitaAssistant Professor (RTDA)
Domenico CiuonzoAssociate Professor
Gabriele MangiacaprePhD Student
Francesco CerasuoloPostdoc
Antonio MontieriTenure-Track Professor
Giuseppe AcetoAssociate Professor
Ciro GuidaPostdoc - Now at Unversité Clermont Auvergne and Université de Strasbourg
Publications
- Conference G. Mangiacapre, F. Cerasuolo, A. Nascita, D. Ciuonzo, A. Pescapè, “Synthetic Network Traffic Generation via Federated Generative AI for Traffic Classification”, NOMS 2026-2026 IEEE Network Operations and Management Symposium, 2026.
- Preprint G. Bovenzi, D. Ciuonzo, J. Krolikowski, A. Montieri, A. Nascita, A. Pescapè, D. Rossi, “Lightweight GenAI for Network Traffic Generation: Fidelity, Augmentation, and Classification”, arXiv (Cornell University), 2026. PDF
- Journal G. Aceto, F. Giampaolo, C. Guida, S. Izzo, A. Pescapè, F. Piccialli, E. Prezioso, “Synthetic and privacy-preserving traffic trace generation using generative AI models for training Network Intrusion Detection Systems”, Journal of Network and Computer Applications, 2024.
- Conference D. Emma, A. Pescapè, G. Ventre, “Analysis and experimentation of an open distributed platform for synthetic”, Proceedings. 10th IEEE International Workshop on Future Trends of Distributed Computing Systems, 2004. FTDCS 2004., 2004.