Repozytorium publikacji - Politechnika Gdańska

Deep Neural Networks (DNN) are state of the art algorithms for image classification. Although significant achievements and perspectives, deep neural networks and accompanying learning algorithms have some important challenges to tackle. However, it appears that it is relatively easy to attack and fool with well-designed input samples called adversarial examples. Adversarial perturba-tions are unnoticeable for humans. Such attacks are a severe threat to the devel-opment of these systems in critical applications, such as medical or military sys-tems. Hence, it is necessary to develop methods of counteracting these attacks. These methods are called defense strategies and aim at increasing the neural mod-el's robustness against adversarial attacks. In this paper, we reviewed the recent findings in adversarial attacks and defense strategies. We also analyzed the ef-fects of attacks and defense strategies applied, using the local and global analyz-ing methods from the family of explainable artificial intelligence.

Autorzy

• Zuzanna Klawikowska link otwiera się w nowej karcie ,
• dr inż. Agnieszka Mikołajczyk link otwiera się w nowej karcie ,
• dr hab. inż. Michał Grochowski link otwiera się w nowej karcie