Publications

2025

1. 

   A Comparative Analysis of Active Learning Strategies for Android Malware Detection

   Cristian Manca, Luca Minnei, Maura Pintor, and 2 more authors

   In 2025 International Conference on Machine Learning and Cybernetics (ICMLC), 2025

   DOI PDF

2. 

   Less is more? an ablation study on AutoAttack for adversarial robustness evaluation

   Luca Melis, Luca Scionis, Fabio Brau, and 2 more authors

   In 2025 International Conference on Machine Learning and Cybernetics (ICMLC), 2025

   DOI PDF
3. ArXiv

   

   Out-of-Distribution Detection for Continual Learning: Design Principles and Benchmarking

   Srishti Gupta, Riccardo Balia, Daniele Angioni, and 7 more authors

   arXiv preprint arXiv:2512.19725, 2025

   PDF
4. ArXiv

   

   SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models

   Giorgio Piras, Raffaele Mura, Fabio Brau, and 3 more authors

   arXiv preprint arXiv:2511.08379, 2025

   PDF
5. ArXiv

   

   Video Deblurring by Sharpness Prior Detection and Edge Information

   Yang Tian, Fabio Brau, Giulio Rossolini, and 2 more authors

   arXiv preprint arXiv:2501.12246, 2025

   PDF
6. ArXiv

   

   S2AP: Score-space Sharpness Minimization for Adversarial Pruning

   Giorgio Piras, Qi Zhao, Fabio Brau, and 3 more authors

   arXiv preprint arXiv:2510.18381, 2025

   PDF
7. NeurIPS

   

   TransferBench: Benchmarking Ensemble-based Black-box Transfer Attacks

   Fabio Brau, Maura Pintor, Antonio Emanuele Cinà, and 5 more authors

   Advances in Neural Information Processing Systems, 2025

   HTML PDF Poster

8. 

   Exploiting edge features for transferable adversarial attacks in distributed machine learning

   Giulio Rossolini, Fabio Brau, Alessandro Biondi, and 2 more authors

   Internet of Things, 2025

   Bib PDF

   @article{rossolini2025exploiting,
     title = {Exploiting edge features for transferable adversarial attacks in distributed machine learning},
     author = {Rossolini, Giulio and Brau, Fabio and Biondi, Alessandro and Biggio, Battista and Buttazzo, Giorgio},
     journal = {Internet of Things},
     pages = {101795},
     year = {2025},
     publisher = {Elsevier},
   }

2024

1. PhD Thesis

   

   Methods for Certifiable Robustness of Deep Neural Networks

   Fabio Brau

   Mar 2024

   Bib PDF

   @phdthesis{brau2024methods,
     title = {Methods for Certifiable Robustness of Deep Neural Networks},
     author = {Brau, Fabio},
     school = {Sant'Anna School of Advanced Studies},
     address = {Pisa, Italy},
     year = {2024},
     month = mar,
     day = {15},
     type = {PhD Thesis},
   }

2. CVPR

   

   1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness

   Bernd Prach, Fabio Brau, Giorgio Buttazzo, and 1 more author

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2024

   Bib PDF Code Poster

   @inproceedings{prach20241,
     author = {Prach, Bernd and Brau, Fabio and Buttazzo, Giorgio and Lampert, Christoph H.},
     title = {1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     month = jun,
     year = {2024},
     pages = {24574-24583},
   }

2023

1. AAAI

   

   Defending from Physically-Realizable Adversarial Attacks through Internal Over-Activation Analysis

   Giulio Rossolini, Federico Nesti, Fabio Brau, and 2 more authors

   Proceedings of the AAAI Conference on Artificial Intelligence, Jun 2023

   Bib PDF

   @article{rossolini2023defending,
     title = {Defending from Physically-Realizable Adversarial Attacks through Internal Over-Activation Analysis},
     volume = {37},
     number = {12},
     journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
     author = {Rossolini, Giulio and Nesti, Federico and Brau, Fabio and Biondi, Alessandro and Buttazzo, Giorgio},
     year = {2023},
     month = jun,
     pages = {15064-15072},
   }

2. AAAI

   

   Robust-by-Design Classification via Unitary-Gradient Neural Networks

   Fabio Brau, Giulio Rossolini, Alessandro Biondi, and 1 more author

   Proceedings of the AAAI Conference on Artificial Intelligence, Jun 2023

   Bib PDF

   @article{brau2023robust,
     title = {Robust-by-Design Classification via Unitary-Gradient Neural Networks},
     volume = {37},
     number = {12},
     journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
     author = {Brau, Fabio and Rossolini, Giulio and Biondi, Alessandro and Buttazzo, Giorgio},
     year = {2023},
     month = jun,
     pages = {14729-14737},
   }

3. 

   Maximizing team synergy in AI-related interdisciplinary groups: an interdisciplinary-by-design iterative methodology

   Piercosma Bisconti, Davide Orsitto, Federica Fedorczyk, and 8 more authors

   AI & SOCIETY, Jun 2023

   Bib PDF

   @article{bisconti2023maximizing,
     title = {Maximizing team synergy in AI-related interdisciplinary groups: an interdisciplinary-by-design iterative methodology},
     author = {Bisconti, Piercosma and Orsitto, Davide and Fedorczyk, Federica and Brau, Fabio and Capasso, Marianna and De Marinis, Lorenzo and Eken, H{\"u}seyin and Merenda, Federica and Forti, Mirko and Pacini, Marco and others},
     journal = {AI \& SOCIETY},
     volume = {38},
     number = {4},
     pages = {1443--1452},
     year = {2023},
     publisher = {Springer},
   }

4. TPAMI

   

   On the Minimal Adversarial Perturbation for Deep Neural Networks With Provable Estimation Error

   Fabio Brau, Giulio Rossolini, Alessandro Biondi, and 1 more author

   IEEE Transactions on Pattern Analysis and Machine Intelligence, Jun 2023

   Bib PDF

   @article{brau2023minimal,
     author = {Brau, Fabio and Rossolini, Giulio and Biondi, Alessandro and Buttazzo, Giorgio},
     journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
     title = {On the Minimal Adversarial Perturbation for Deep Neural Networks With Provable Estimation Error},
     year = {2023},
     volume = {45},
     number = {4},
     pages = {5038-5052},
     keywords = {Perturbation methods;Robustness;Estimation;Neural networks;Deep learning;Error analysis;Computational modeling;Adversarial robustness;deep neural networks;trustworthy AI;verification methods},
   }

2021

1. 

   Using Self-Organizing Maps for the Behavioral Analysis of Virtualized Network Functions

   Giacomo Lanciano, Antonio Ritacco, Fabio Brau, and 5 more authors

   In Cloud Computing and Services Science, Jun 2021

   Bib PDF

   @inproceedings{lanciano2021using,
     author = {Lanciano, Giacomo and Ritacco, Antonio and Brau, Fabio and Cucinotta, Tommaso and Vannucci, Marco and Artale, Antonino and Barata, Joao and Sposato, Enrica},
     editor = {Ferguson, Donald and Pahl, Claus and Helfert, Markus},
     title = {Using Self-Organizing Maps for the Behavioral Analysis of Virtualized Network Functions},
     booktitle = {Cloud Computing and Services Science},
     year = {2021},
     publisher = {Springer International Publishing},
     address = {Cham},
     pages = {153--177},
   }

2. 

   Forecasting operation metrics for virtualized network functions

   Tommaso Cucinotta, Giacomo Lanciano, Antonio Ritacco, and 7 more authors

   In 2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid), Jun 2021

   Bib PDF

   @inproceedings{cucinotta2021forecasting,
     title = {Forecasting operation metrics for virtualized network functions},
     author = {Cucinotta, Tommaso and Lanciano, Giacomo and Ritacco, Antonio and Brau, Fabio and Galli, Filippo and Iannino, Vincenzo and Vannucci, Marco and Artale, Antonino and Barata, Joao and Sposato, Enrica},
     booktitle = {2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid)},
     pages = {596--605},
     year = {2021},
     organization = {IEEE},
   }