no code implementations • 15 Dec 2023 • Chandresh Pravin, Ivan Martino, Giuseppe Nicosia, Varun Ojha
We define three \textit{filtering scores} for quantifying the fragility, robustness and antifragility characteristics of DNN parameters based on the performances for (i) clean dataset, (ii) adversarial dataset, and (iii) the difference in performances of clean and adversarial datasets.
no code implementations • 31 Jan 2022 • Chandresh Pravin, Ivan Martino, Giuseppe Nicosia, Varun Ojha
In this paper, we evaluate the robustness of state-of-the-art image classification models trained on the MNIST and CIFAR10 datasets against the fast gradient sign method attack, a simple yet effective method of deceiving neural networks.