TY - GEN
T1 - Target-X
T2 - 47th IEEE Annual Computers, Software, and Applications Conference, COMPSAC 2023
AU - Khamaiseh, Samer Y.
AU - Bagagem, Derek
AU - Al-Alaj, Abdullah
AU - Mancino, Mathew
AU - Alomari, Hakem
AU - Aleroud, Ahmed
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Deep neural networks (DNNs) have achieved a series of significant successes in a wide spectrum of critical domains. For instance, in the field of computer vision, DNNs become the first choice in developing image recognition and classification solutions. However, DNNs have been recently found vulnerable to manipulations of input samples, called adversarial images. The adversarial images can be classified into two categories: untargeted adversarial images which aim to manipulate the output of the DNNs to any incorrect label and targeted adversarial images which force the prediction of the DNNs to a specified target label predefined by the adversary. That being said, the construction of targeted adversarial images requires careful crafting of the targeted perturbations. Different research works have been done to generate targeted adversarial images. However, the majority of them have two limitations: (1) adding large size of perturbations to generate successfully targeted images, and (2) they require extensive computational resources to be utilized in large-scale datasets. This paper introduces Target-X, a novel and fast method for the construction of adversarial targeted images on large-scale datasets that can fool the state-of-the-art image classification neural networks. We evaluate the performance of Target-X using the well-trained image classification neural networks of different architectures and compare it with the well-known T-FGSM and T-UAP targeted attacks. The reported results demonstrate that Target-X can generate targeted adversarial images with the least perturbations on large-scale datasets that can fool the image classification neural networks and significantly outperform the T-FGSM and T-UAP attacks.
AB - Deep neural networks (DNNs) have achieved a series of significant successes in a wide spectrum of critical domains. For instance, in the field of computer vision, DNNs become the first choice in developing image recognition and classification solutions. However, DNNs have been recently found vulnerable to manipulations of input samples, called adversarial images. The adversarial images can be classified into two categories: untargeted adversarial images which aim to manipulate the output of the DNNs to any incorrect label and targeted adversarial images which force the prediction of the DNNs to a specified target label predefined by the adversary. That being said, the construction of targeted adversarial images requires careful crafting of the targeted perturbations. Different research works have been done to generate targeted adversarial images. However, the majority of them have two limitations: (1) adding large size of perturbations to generate successfully targeted images, and (2) they require extensive computational resources to be utilized in large-scale datasets. This paper introduces Target-X, a novel and fast method for the construction of adversarial targeted images on large-scale datasets that can fool the state-of-the-art image classification neural networks. We evaluate the performance of Target-X using the well-trained image classification neural networks of different architectures and compare it with the well-known T-FGSM and T-UAP targeted attacks. The reported results demonstrate that Target-X can generate targeted adversarial images with the least perturbations on large-scale datasets that can fool the image classification neural networks and significantly outperform the T-FGSM and T-UAP attacks.
KW - adversarial deep neural networks
KW - adversarial images
KW - deep learning
KW - image classification neural networks
UR - http://www.scopus.com/inward/record.url?scp=85168876808&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85168876808&partnerID=8YFLogxK
U2 - 10.1109/COMPSAC57700.2023.00087
DO - 10.1109/COMPSAC57700.2023.00087
M3 - Conference contribution
AN - SCOPUS:85168876808
T3 - Proceedings - International Computer Software and Applications Conference
SP - 617
EP - 626
BT - Proceedings - 2023 IEEE 47th Annual Computers, Software, and Applications Conference, COMPSAC 2023
A2 - Shahriar, Hossain
A2 - Teranishi, Yuuichi
A2 - Cuzzocrea, Alfredo
A2 - Sharmin, Moushumi
A2 - Towey, Dave
A2 - Majumder, AKM Jahangir Alam
A2 - Kashiwazaki, Hiroki
A2 - Yang, Ji-Jiang
A2 - Takemoto, Michiharu
A2 - Sakib, Nazmus
A2 - Banno, Ryohei
A2 - Ahamed, Sheikh Iqbal
PB - IEEE Computer Society
Y2 - 26 June 2023 through 30 June 2023
ER -