93 citations · 114 across the 5 of their papers we have counts for
10 papers
Gauge-invariant coefficients in perturbative quantum gravity
Fiorenzo Bastianelli, Roberto Bonezzi, Marco Melis
Heat kernel methods are useful for studying properties of quantum gravity. We recompute here the first three heat kernel coefficients in perturbative quantum gravity with cosmologi…
FADER: Fast Adversarial Example Rejection
Francesco Crecchi, Marco Melis, Angelo Sotgiu +2
Deep neural networks are vulnerable to adversarial examples, i.e., carefully-crafted inputs that mislead classification at test time. Recent defenses have been shown to improve adv…
Do Gradient-based Explanations Tell Anything About Adversarial Robustness to Android Malware?
Marco Melis, Michele Scalas, Ambra Demontis +4
While machine-learning algorithms have demonstrated a strong ability in detecting Android malware, they can be evaded by sparse evasion attacks crafted by injecting a small set of…
secml: A Python Library for Secure and Explainable Machine Learning
Maura Pintor, Luca Demetrio, Angelo Sotgiu +3
We present \texttt{secml}, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including tes…
Deep Neural Rejection against Adversarial Examples
Angelo Sotgiu, Ambra Demontis, Marco Melis +4
Despite the impressive performances reported by deep neural networks in different application domains, they remain largely vulnerable to adversarial examples, i.e., input samples t…
Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks
Ambra Demontis, Marco Melis, Maura Pintor +5
Transferability captures the ability of an attack against a machine-learning model to be effective against a different, potentially unknown, model. Empirical evidence for transfera…