-
Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference
Adversarial reprogramming allows repurposing a machine-learning model to...
08/26/2021 ∙ by Yang Zheng, et al. ∙
20
∙
share
read it
-
Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples
Evaluating robustness of machine-learning models to adversarial examples...
06/18/2021 ∙ by Maura Pintor, et al. ∙
25
∙
share
read it
-
Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints
Evaluating adversarial robustness amounts to finding the minimum perturb...
02/25/2021 ∙ by Maura Pintor, et al. ∙
14
∙
share
read it
-
Detecting Anomalies from Video-Sequences: a Novel Descriptor
We present a novel descriptor for crowd behavior analysis and anomaly de...
10/13/2020 ∙ by Giulia Orrù, et al. ∙
0
∙
share
read it
-
secml: A Python Library for Secure and Explainable Machine Learning
We present secml, an open-source Python library for secure and explainab...
12/20/2019 ∙ by Marco Melis, et al. ∙
122
∙
share
read it
-
On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks
Transferability captures the ability of an attack against a machine-lear...
09/08/2018 ∙ by Ambra Demontis, et al. ∙
0
∙
share
read it
