@inproceedings{ManGiaAli-24-IJCLR-IC,
author = {Manhaeve, Robin
and Giannini, Francesco
and Ali, Mehdi
and Azzolini, Damiano
and Bizzarri, Alice
and Borghesi, Andrea
and Bortolotti, Samuele
and De Raedt, Luc
and Dhami, Devendra
and Diligenti, Michelangelo
and Duman{\v{c}}i{\'{c}}, Sebastijan
and Faltings, Boi
and Gentili, Elisabetta
and Gerevini, Alfonso
and Gori, Marco
and Guns, Tias
and Homola, Martin
and Kersting, Kristian
and Lehmann, Jens
and Lombardi, Michele
and Lorello, Luca
and Marconato, Emanuele
and Melacci, Stefano
and Passerini, Andrea
and Paul, Debjit
and Riguzzi, Fabrizio
and Teso, Stefano
and Yorke-Smith, Neil
and Lippi, Marco},
editor = {Dai, Wang-Zhou},
title = {Benchmarking in Neuro-Symbolic AI},
booktitle = {Learning and Reasoning: 4th International Joint Conference on Learning and Reasoning, IJCLR 2024, and 33rd International Conference on Inductive Logic Programming, ILP 2024, Nanjing, China, September 20--22, 2024, Proceedings},
year = {2026},
publisher = {Springer Nature Switzerland},
address = {Cham},
pages = {238--249},
abstract = {Neural-symbolic (NeSy) AI has gained a lot of popularity by enhancing learning models with explicit reasoning capabilities. Both new systems and new benchmarks are constantly introduced and used to evaluate learning and reasoning skills. The large variety of systems and benchmarks, however, makes it difficult to establish a fair comparison among the various frameworks, let alone a unifying set of benchmarking criteria. This paper analyzes the state-of-the-art in benchmarking NeSy systems, studies its limitations, and proposes ways to overcome them. We categorize popular neural-symbolic frameworks into three groups: model-theoretic, proof-theoretic fuzzy, and proof-theoretic probabilistic systems. We show how these three categories have distinct strengths and weaknesses, and how this is reflected in the type of tasks and benchmarks to which they are applied.},
doi = {10.1007/978-3-032-09087-4_17},
isbn = {978-3-032-09087-4}
}
@article{BizChuJai25-JISA-IJ,
title = {Neurosymbolic AI for network intrusion detection systems: A survey},
journal = {Journal of Information Security and Applications},
volume = {94},
pages = {104205},
year = {2025},
issn = {2214-2126},
doi = {10.1016/j.jisa.2025.104205},
url = {https://www.sciencedirect.com/science/article/pii/S221421262500242X},
author = {Alice Bizzarri and Chung-En (Johnny) Yu and Brian Jalaian and Fabrizio Riguzzi and Nathaniel D. Bastian},
keywords = {Neurosymbolic artificial intelligence, Network intrusion detection system, Cybersecurity, Artificial intelligence}
}
@inproceedings{ManGia25-IJCLR-IC,
title = {Benchmarking in Neuro-Symbolic AI},
author = {Manhaeve, Robin and Giannini, Francesco and Ali, Mehdi and Azzolini, Damiano and Bizzarri, Alice and Borghesi, Andrea and Bortolotti, Samuele and De Raedt, Luc and Dhami, Devendra and Diligenti, Michelangelo and Sebastijan Dumancic and Boi Faltings and Elisabetta Gentili and Alfonso Gerevini and Marco Gori and Tias Guns and Martin Homola and Kristian Kersting and Jens Lehmann and Michele Lombardi and Luca Lorello and Emanuele Marconato and Stefano Melacci and Andrea Passerini and Debjit Paul and Fabrizio Riguzzi and Stefano Teso and Neil Yorke-Smith and Marco Lippi},
booktitle = {Proceedings of The 4th International Joint Conference on Learning \& Reasoning},
year = {2025}
}
@inproceedings{BizYouJalRigBas24-AIXIA-IC,
author = {Bizzarri, Alice
and Yu, Chung-En
and Jalaian, Brian
and Riguzzi, Fabrizio
and Bastian, Nathaniel D.},
editor = {Artale, Alessandro
and Cortellessa, Gabriella
and Montali, Marco},
title = {Neuro-Symbolic Integration for Open Set Recognition in Network Intrusion Detection},
booktitle = {AIxIA 2024 -- Advances in Artificial Intelligence},
year = {2025},
publisher = {Springer Nature Switzerland},
address = {Cham},
pages = {50--63},
abstract = {Open Set Recognition (OSR) addresses the challenge of classifying inputs into known and unknown categories, a crucial task where labeling is often prohibitively expensive or incomplete. This is particularly vital in applications like Network Intrusion Detection Systems (NIDS), where OSR is used to identify novel, previously unknown attacks. We propose a neuro-symbolic integration approach that combines deep learning and symbolic methods, enhancing deep embedding for clustering with custom loss functions and leveraging XGBoost's decision tree algorithms. Our methodology not only robustly addresses the identification of previously unknown attacks in NIDS but also effectively manages scenarios involving covariance shift. We demonstrate the efficacy of our approach through extensive experimentation, achieving an AUROC of 0.99 in both contexts. This paper presents a significant step forward in OSR for network intrusion detection by integrating deep and symbolic learning to handle unforeseen challenges in dynamic environments.},
isbn = {978-3-031-80607-0},
doi = {10.1007/978-3-031-80607-0_5}
}
This file was generated by bibtex2html 1.98.