Emanuele Ledda

According to our database, Emanuele Ledda authored at least 10 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of five.

2024

On the Robustness of Adversarial Training Against Uncertainty Attacks.

Emanuele Ledda, Giovanni Scodeller, Daniele Angioni, Giorgio Piras, Antonio Emanuele Cinà, Giorgio Fumera, Battista Biggio, Fabio Roli

CoRR, 2024

2023

Dropout injection at test time for post hoc uncertainty quantification in neural networks.

Emanuele Ledda, Giorgio Fumera, Fabio Roli

Inf. Sci., October, 2023

Trustworthy AI in Video Surveillance: The IMMAGINA Project.

Emanuele Ledda, Lorenzo Putzu, Rita Delussu, Giorgio Fumera, Fabio Roli

Proceedings of the Italia Intelligenza Artificiale, 2023

Evaluation of Robustness Metrics for Defense of Machine Learning Systems.

J. DeMarchi, R. Rijken, J. Melrose, B. Madahar, Giorgio Fumera, Fabio Roli, Emanuele Ledda, Metin Aktas, Frank Kurth, Paul M. Baggenstoss, Björn Pelzer, L. Kanestad

Proceedings of the International Conference on Military Communications and Information Systems, 2023

BLUES: Before-reLU-EStimates Bayesian Inference for Crowd Counting.

Emanuele Ledda, Rita Delussu, Lorenzo Putzu, Giorgio Fumera, Fabio Roli

Proceedings of the Image Analysis and Processing - ICIAP 2023, 2023

Human-in-the-Loop Person Re-Identification as a Defence Against Adversarial Attacks.

Rita Delussu, Lorenzo Putzu, Emanuele Ledda, Giorgio Fumera

Proceedings of the Image Analysis and Processing - ICIAP 2023 Workshops, 2023

Adversarial Attacks Against Uncertainty Quantification.

Emanuele Ledda, Daniele Angioni, Giorgio Piras, Giorgio Fumera, Battista Biggio, Fabio Roli

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022

On the Evaluation of Video-Based Crowd Counting Models.

Emanuele Ledda, Lorenzo Putzu, Rita Delussu, Giorgio Fumera, Fabio Roli

Proceedings of the Image Analysis and Processing - ICIAP 2022, 2022

2021

Applying Long-Short Term Memory Recurrent Neural Networks for Real-Time Stroke Recognition.

Emanuele Ledda, Lucio Davide Spano

Proceedings of the EICS '21: ACM SIGCHI Symposium on Engineering Interactive Computing Systems, 2021

How Realistic Should Synthetic Images Be for Training Crowd Counting Models?

Emanuele Ledda, Lorenzo Putzu, Rita Delussu, Andrea Loddo, Giorgio Fumera

Proceedings of the Computer Analysis of Images and Patterns, 2021