Francesco Croce

activity

20182026

most citedReliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks

598 citations · 1k across the 30 of their papers we have counts for

collaborators

Showing 2021 · cs.LGShow all

2 papers · 2 filters

cs.LG2021★ 1 cited

Adversarial Robustness against Multiple and Single $l_{p}$ -Threat Models via Quick Fine-Tuning of Robust Classifiers

Francesco Croce, Matthias Hein

A major drawback of adversarially robust models, in particular for large scale datasets like ImageNet, is the extremely long training time compared to standard ones. Moreover, mode…

cs.LG2021★ 4 cited

Mind the box: $l_{1}$ -APGD for sparse adversarial attacks on image classifiers

Francesco Croce, Matthias Hein

We show that when taking into account also the image domain $[0, 1]^{d}$ , established $l_{1}$ -projected gradient descent (PGD) attacks are suboptimal as they do not consider that the ef…

Adversarial Robustness against Multiple and Single lp​-Threat Models via Quick Fine-Tuning of Robust Classifiers

Mind the box: l1​-APGD for sparse adversarial attacks on image classifiers

Adversarial Robustness against Multiple and Single $l_{p}$ -Threat Models via Quick Fine-Tuning of Robust Classifiers

Mind the box: $l_{1}$ -APGD for sparse adversarial attacks on image classifiers