Federica Granese — accepted AI-conference papers

2024

Optimal Zero-Shot Detector for Multi-Armed Attacks

Federica Granese, Marco Romanelli, Pablo Piantanida

AISTATS 2024poster

This research delves into a scenario where a malicious actor can manipulate data samples using a multi-armed attack strategy, providing them with multiple ways to introduce noise into the data sample. Our central objective is to protect the data by detecting any alterations to the input. We approach…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2021

DOCTOR: A Simple Method for Detecting Misclassification Errors

Federica Granese, Marco Romanelli, Daniele Gorla, Catuscia Palamidessi, Pablo Piantanida

NeurIPS 2021spotlight

Deep neural networks (DNNs) have shown to perform very well on large scale object recognition problems and lead to widespread use for real-world applications, including situations where DNN are implemented as “black boxes”. A promising approach to secure their use is to accept decisions that are li…

Cited by 57 Source ↗PDF ↗code ↗Scholar ↗