In the framework of Adversarial Machine Learning, several detection and protection techniques are used to characterize specific attack-defense scenarios. In this paper, we present universal, unrestricted black-box adversarial attacks based on a multi-objective nested evolutionary algorithm able to incorporate the detection rate and a measure of image quality into the attack building phase.
Combining Attack Success Rate and Detection Rate for effective Universal Adversarial Attacks
Baia A. E.;Milani A.;Poggioni V.
2021
Abstract
In the framework of Adversarial Machine Learning, several detection and protection techniques are used to characterize specific attack-defense scenarios. In this paper, we present universal, unrestricted black-box adversarial attacks based on a multi-objective nested evolutionary algorithm able to incorporate the detection rate and a measure of image quality into the attack building phase.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.