Defending against substitute model black box adversarial attacks with the 01 loss

A Novel Data-Driven Attack Method on Machine Learning Models.

E Sadıkoğlu, İ Kösesoy, M Gök - Journal of Universal …, 2024 - search.ebscohost.com
With the increasing popularity and usage of artificial intelligence systems, it has become
crucial to address their vulnerability to cyber-attacks. In this study, we propose a novel …
Uložit Citovat Počet citací tohoto článku: 1 Související články Všechny verze (počet: 2)

Accurate and adversarially robust classification of medical images and ECG time-series with gradient-free trained sign activation neural networks

Z Yang, Y Yang, Y Xue, FY Shih, J Ady… - … on Bioinformatics and …, 2020 - ieeexplore.ieee.org
Adversarial attacks in medical AI imaging systems can lead to misdiagnosis and insurance
fraud as recently highlighted by Finlayson et. al. in Science 2019. They can also be carried …
Uložit Citovat Počet citací tohoto článku: 8 Související články Všechny verze (počet: 3)