30 citations · 54 across the 11 of their papers we have counts for
11 papers
Ensembling Uncertainty Measures to Improve Safety of Black-Box Classifiers
Tommaso Zoppi, Andrea Ceccarelli, Andrea Bondavalli
Machine Learning (ML) algorithms that perform classification may predict the wrong class, experiencing misclassifications. It is well-known that misclassifications may have cascadi…
On the Efficacy of Metrics to Describe Adversarial Attacks
Tommaso Puccetti, Tommaso Zoppi, Andrea Ceccarelli
Adversarial defenses are naturally evaluated on their ability to tolerate adversarial attacks. To test defenses, diverse adversarial attacks are crafted, that are usually described…
Evaluating Object (mis)Detection from a Safety and Reliability Perspective: Discussion and Measures
Andrea Ceccarelli, Leonardo Montecchi
We argue that object detectors in the safety critical domain should prioritize detection of objects that are most likely to interfere with the actions of the autonomous actor. Espe…
Prepare for Trouble and Make it Double. Supervised and Unsupervised Stacking for AnomalyBased Intrusion Detection
Tommaso Zoppi, Andrea Ceccarelli
In the last decades, researchers, practitioners and companies struggled in devising mechanisms to detect malicious activities originating security threats. Amongst the many solutio…
Attacks and Faults Injection in Self-Driving Agents on the Carla Simulator -- Experience Report
Niccolò Piazzesi, Massimo Hong, Andrea Ceccarelli
Machine Learning applications are acknowledged at the foundation of autonomous driving, because they are the enabling technology for most driving tasks. However, the inclusion of t…
Unsupervised Anomaly Detectors to Detect Intrusions in the Current Threat Landscape
Tommaso Zoppi, Andrea ceccarelli, Tommaso Capecchi +1
Anomaly detection aims at identifying unexpected fluctuations in the expected behavior of a given system. It is acknowledged as a reliable answer to the identification of zero-day…