Recent research has found that neural networks are vulnerable to several types of adversarial attacks, where the input samples are modified in such a way that the model produces a wrong prediction that misclassifies the adversarial sample. In this paper we focus on black-box adversarial attacks, that can be performed without knowing the inner structure of the attacked model, nor the training procedure, and we propose a novel attack that is capable of correctly attacking a high percentage of samples by rearranging a small number of pixels within the attacked image. We demonstrate that our attack works on a large number of datasets and models, that it requires a small number of iterations, and that the distance between the original sample and the adversarial one is negligible to the human eye.
Pixle: a fast and effective black-box attack based on rearranging pixels / Pomponi, Jary; Scardapane, Simone; Uncini, Aurelio. - (2022), pp. 1-7. [10.1109/IJCNN55064.2022.9892966].
Pixle: a fast and effective black-box attack based on rearranging pixels
Pomponi, Jary
Primo
;Scardapane, SimoneSecondo
;Uncini, AurelioUltimo
2022
Abstract
Recent research has found that neural networks are vulnerable to several types of adversarial attacks, where the input samples are modified in such a way that the model produces a wrong prediction that misclassifies the adversarial sample. In this paper we focus on black-box adversarial attacks, that can be performed without knowing the inner structure of the attacked model, nor the training procedure, and we propose a novel attack that is capable of correctly attacking a high percentage of samples by rearranging a small number of pixels within the attacked image. We demonstrate that our attack works on a large number of datasets and models, that it requires a small number of iterations, and that the distance between the original sample and the adversarial one is negligible to the human eye.File | Dimensione | Formato | |
---|---|---|---|
Pomponi_Rearranging-pixels_2022.pdf
accesso aperto
Note: Articolo completo
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Creative commons
Dimensione
1.25 MB
Formato
Adobe PDF
|
1.25 MB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.