@inproceedings{SAIL:2026-verifying-the-verifier-what-a-guardrail,
author = {S. Varghese and A. Lomuscio},
title = {{Verifying the Verifier: What a Guardrail Certificate Pays For}},
booktitle = {NeurIPS26 Workshop Verify-Agents. Sydney, Australia. Poster},
year = {2026},
url = {https://openreview.net/forum?id=6RIDw4SNGo}
}
NeurIPS WS 2026
Intent-Preserving Adversarial User Simulation for Multi-Turn Agent Evaluation
@inproceedings{SAIL:2026-intent-preserving-adversarial-user-simulation-for,
author = {A. V. Sharma and B. Formento and A. Lomuscio},
title = {{Intent-Preserving Adversarial User Simulation for Multi-Turn Agent Evaluation}},
booktitle = {NeurIPS26 Workshop on Grounded User Simulation for Model Evaluation and Training: Diversity, Fidelity, and Validity (UserSim). Paris, France. Spotlight presentation},
year = {2026},
url = {https://openreview.net/forum?id=Ml0KxdEl5Q}
}
NeurIPS 2026
End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps
@inproceedings{SAIL:2026-end-to-end-verification-of-neuro,
author = {A. Hekal and V. Manginas and N. Manginas and A. Lomuscio},
title = {{End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps}},
booktitle = {Proceedings of the 40th Annual Conference on Neural Information Processing Systems (NeurIPS26). Paris, France},
year = {2026}
}
arXiv 2026
Validating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action Models
@article{DBLP:journals/corr/abs-2609-22293,
author = {Bogdan Aron and Christopher Brix and Benedikt Brückner and Yanghao Zhang and Panagiotis Kouvaros and Alessio Lomuscio},
title = {{Validating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action Models}},
journal = {CoRR},
volume = {abs/2609.22293},
year = {2026},
eprinttype = {arXiv},
eprint = {2609.22293},
doi = {10.48550/ARXIV.2609.22293}
}
COLM 2026
Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks
@inproceedings{DBLP:conf/eccv/BrucknerMZKL26,
author = {Benedikt Brückner and Alejandro J. Mercado and Yanghao Zhang and Panagiotis Kouvaros and Alessio Lomuscio},
title = {{IoUCert: Robustness Verification for Anchor-Based Object Detectors}},
booktitle = {Computer Vision - ECCV 2026 - 19th European Conference, Malmö, Sweden, September 8-12, 2026, Proceedings, Part XXI},
series = {Lecture Notes in Computer Science},
volume = {17021},
pages = {364--384},
publisher = {Springer},
year = {2026},
doi = {10.1007/978-3-032-37574-2_20}
}
SAIV 2026
Hybrid Robustness Verification for Spatio-Temporal Neural Networks
@inproceedings{DBLP:conf/saiv/VargheseWL26,
author = {Sherwin Varghese and Matthew Wicker and Alessio Lomuscio},
title = {{Hybrid Robustness Verification for Spatio-Temporal Neural Networks}},
booktitle = {AI Verification - Third International Symposium, SAIV 2026, Lisbon, Portugal, July 24-25, 2026, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {16831},
pages = {3--35},
publisher = {Springer},
year = {2027},
doi = {10.1007/978-3-032-32357-6_1}
}
CVPR-F 2026
A Robust Out-of-Distribution Detection Framework via Synergistic Smoothing
@inproceedings{DBLP:conf/cvpr/DurandKGL26,
author = {Jean-Guillaume Durand and Panagiotis Kouvaros and Maxime Gariel and Alessio Lomuscio},
title = {{Lipschitz Optimization for Formal Verification of Homographies}},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2026, Denver, CO, USA, June 3-7, 2026},
pages = {13306--13315},
publisher = {Computer Vision Foundation},
year = {2026},
url = {https://openaccess.thecvf.com/content/CVPR2026/html/Durand_Lipschitz_Optimization_for_Formal_Verification_of_Homographies_CVPR_2026_paper.html}
}
IJCAI WS 2026
Out-of-Distribution Detection using Counterfactual Distance
@inproceedings{DBLP:conf/ifaamas/LinWTLL26,
author = {Zhihao Lin and Lin Wu and Zhen Tian and Alessio Lomuscio and Jianglin Lan},
title = {{Scalable and Safe Multi-Agent Coordination with Reconstructed Level-k Monte Carlo Tree Search}},
booktitle = {Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2026, Paphos, Cyprus, May 25-29, 2026},
pages = {394--402},
publisher = {ACM},
year = {2026},
url = {https://dl.acm.org/doi/10.65109/TAVV6081}
}
AAAI WS 2026
Certified Background-Invariant Training via Latent Generative Models
@inproceedings{SAIL:2026-certified-background-invariant-training-via-latent,
author = {B. Brückner and H. Hanspal and A. Lomuscio},
title = {{Certified Background-Invariant Training via Latent Generative Models}},
booktitle = {Proceedings of the AAAI26 Workshop on Artificial Intelligence for Air Transportation (AI4AT). Singapore},
year = {2026}
}
AAAI WS 2026
Certified Training for Convolutional Perturbations
@article{DBLP:journals/corr/abs-2608-03609,
author = {Alejandro J. Mercado and Alessio Lomuscio},
title = {{Formal Verification of Agentic Systems over Operational Data}},
journal = {CoRR},
volume = {abs/2608.03609},
year = {2026},
eprinttype = {arXiv},
eprint = {2608.03609},
doi = {10.48550/ARXIV.2608.03609}
}
2025
NeurIPS 2025
Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation
@inproceedings{DBLP:conf/nips/ZhangKL25,
author = {Yanghao Zhang and Panagiotis Kouvaros and Alessio Lomuscio},
title = {{Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation}},
booktitle = {Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, NeurIPS 2025, San Diego, CA, USA, December 2-7, 2025 / Mexico City, Mexico, November 30 - December 5, 2025},
year = {2025},
url = {http://papers.nips.cc/paper_files/paper/2025/hash/1435ac9924d7621e44aa2407a1cfdec7-Abstract-Conference.html}
}
@inproceedings{DBLP:conf/ecai/HanspalL25,
author = {Harleen Hanspal and Alessio Lomuscio},
title = {{Verifiably Robust Contrastive Learning}},
booktitle = {ECAI 2025 - 28th European Conference on Artificial Intelligence, 25-30 October 2025, Bologna, Italy - Including 14th Conference on Prestigious Applications of Intelligent Systems (PAIS 2025)},
series = {Frontiers in Artificial Intelligence and Applications},
volume = {413},
pages = {1559--1566},
publisher = {IOS Press},
year = {2025},
doi = {10.3233/FAIA250980}
}
NeSy 2025
A Scalable Approach to Probabilistic Neuro-Symbolic Robustness Verification
V. Manginas, N. Manginas, E. Stevinson, S. Varghese, N. Katzouris, G. Paliouras, A. Lomuscio
@inproceedings{DBLP:conf/nesy/ManginasMSVKPL25,
author = {Vasileios Manginas and Nikolaos Manginas and Edward Stevinson and Sherwin Varghese and Nikos Katzouris and Georgios Paliouras and Alessio Lomuscio},
title = {{A Scalable Approach to Probabilistic Neuro-Symbolic Robustness Verification}},
booktitle = {Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning (NeSy 2025), 8-10 September 2025, Santa Cruz, CA, USA},
series = {Proceedings of Machine Learning Research},
volume = {284},
pages = {52--69},
publisher = {PMLR},
year = {2025},
url = {https://proceedings.mlr.press/v284/manginas25a.html}
}
UAI 2025
Learning Robust XGBoost Ensembles for Regression Tasks
@inproceedings{DBLP:conf/uai/SharmaKL25,
author = {Atri Vivek Sharma and Panagiotis Kouvaros and Alessio Lomuscio},
title = {{Learning Robust XGBoost Ensembles for Regression Tasks}},
booktitle = {Conference on Uncertainty in Artificial Intelligence, Rio Othon Palace, Rio de Janeiro, Brazil, 21-25 July 2025},
series = {Proceedings of Machine Learning Research},
volume = {286},
pages = {3809--3825},
publisher = {PMLR},
year = {2025},
url = {https://proceedings.mlr.press/v286/sharma25a.html}
}
CVPR WS 2025
Improving Weather-based OOD Generalisation in Lidar-based Object Detection Models via Adversarial Training
@inproceedings{DBLP:conf/wacv/HanspalPL25,
author = {Harleen Hanspal and Alessandro De Palma and Alessio Lomuscio},
title = {{Robustness to Perturbations in the Frequency Domain: Neural Network Verification and Certified Training}},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025 - Workshops, Tucson, AZ, USA, February 28 - March 4, 2025},
pages = {591--600},
publisher = {IEEE},
year = {2025},
doi = {10.1109/WACVW65960.2025.00071}
}