Giulio Rossolini | Scuola Superiore Sant'Anna

Bio

Giulio is a postdoctoral researcher at the Real-Time Systems Laboratory of the Scuola Superiore Sant’Anna in Pisa. He earned a degree in Embedded Computing Systems Engineering, a Master’s Degree jointly offered by the Scuola Superiore Sant’Anna of Pisa and the University of Pisa, in 2020. He received a Ph.D. in Emerging Digital Technologies in 2024, focusing on safety and robustness issues in artificial intelligence algorithms for cyber-physical systems. His current research interests include designing and implementing software tools to enhance the trustworthiness of machine learning algorithms used in computer vision applications and distributed learning-enabled environments.

Publications

Rossolini, Giulio; Nesti, Federico; D'Amico, Gianluca; Nair, Saasha; Biondi, Alessandro; Buttazzo, Giorgio

On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving Open new browser tab

(2023)
D’Amico, Gianluca; Marinoni, Mauro; Nesti, Federico; Rossolini, Giulio; Buttazzo, Giorgio; Sabina, Salvatore; Lauro, Gianluigi

TrainSim: A Railway Simulation Framework for LiDAR and Camera Dataset Generation Open new browser tab

(2023)
Rossolini, Giulio; Nesti, Federico; Brau, Fabio; Biondi, Alessandro; Buttazzo, Giorgio

Defending from Physically-Realizable Adversarial Attacks through Internal Over-Activation Analysis Open new browser tab

(2023)
Brau, F.; Rossolini, G.; Biondi, A.; Buttazzo, G.

Robust-by-Design Classification via Unitary-Gradient Neural Networks Open new browser tab

(2023)
Nesti, Federico; Rossolini, Giulio; Nair, Saasha; Biondi, Alessandro; Buttazzo, Giorgio Carlo

Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks Open new browser tab

(2022)
Rossolini, Giulio; Biondi, Alessandro; Buttazzo, Giorgio

Increasing the Confidence of Deep Neural Networks by Coverage Analysis Open new browser tab

(2022)
Brau, F.; Rossolini, G.; Biondi, A.; Buttazzo, G.

On the Minimal Adversarial Perturbation for Deep Neural Networks With Provable Estimation Error Open new browser tab

(2022)

Bio

Publications

On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving Open new browser tab

TrainSim: A Railway Simulation Framework for LiDAR and Camera Dataset Generation Open new browser tab

Defending from Physically-Realizable Adversarial Attacks through Internal Over-Activation Analysis Open new browser tab

Robust-by-Design Classification via Unitary-Gradient Neural Networks Open new browser tab

Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks Open new browser tab

Increasing the Confidence of Deep Neural Networks by Coverage Analysis Open new browser tab

On the Minimal Adversarial Perturbation for Deep Neural Networks With Provable Estimation Error Open new browser tab