On the Properties of Adversarially-Trained CNNs

no code implementations • 17 Mar 2022 • Mattia Carletti, Matteo Terzi, Gian Antonio Susto

Adversarial Training has proved to be an effective training paradigm to enforce robustness against adversarial examples in modern neural network architectures.

AcME -- Accelerated Model-agnostic Explanations: Fast Whitening of the Machine-Learning Black Box

no code implementations • 23 Dec 2021 • David Dandolo, Chiara Masiero, Mattia Carletti, Davide Dalle Pezze, Gian Antonio Susto

In the context of human-in-the-loop Machine Learning applications, like Decision Support Systems, interpretability approaches should provide actionable insights without making the users wait.

BIG-bench Machine Learning Feature Importance

Improving Robustness with Image Filtering

no code implementations • 21 Dec 2021 • Matteo Terzi, Mattia Carletti, Gian Antonio Susto

By leveraging the IGE representation, we build a new defense method, Filtering As a Defense, that does not allow the attacker to entangle pixels to create malicious patterns.

Adversarial Robustness Data Augmentation

Interpretable Anomaly Detection with DIFFI: Depth-based Isolation Forest Feature Importance

1 code implementation • 21 Jul 2020 • Mattia Carletti, Matteo Terzi, Gian Antonio Susto

Anomaly Detection is an unsupervised learning task aimed at detecting anomalous behaviours with respect to historical data.

Feature Importance feature selection +1