Page 12 - IJEEE-2022-Vol18-ISSUE-1

8 | Kadhim & Al-Darraji
VI. CONCLUSION
To distinguish between original and adversarial
images, a CNN algorithm was used. Therefore, ten classes
were used for ten people. That means each class for every
person and everyone has many different captures of images
with different positions. Thus, classes were divided into
groups of train and test datasets. So, every person has two
folders for both train and test images. However, the number
of train images should be more than the images in the test to
get clear results. Hence, the first method is by training
original images on the CNN algorithm. So, the rate of
recognition is "95%" between train images and test images.
For future work, The number of attacks can be
increased to distort images such as One Pixel attack, Carlini
& Wagner attacks (C&W), Visible Light-based attack
(VLA), AdvHat attack, Face Friend-safe attack, etc. The
number of classes can also be increased with new images.
CONFLICT OF INTEREST
The authors have no conflict of relevant interest to this [14] N. Carlini and D. Wagner, "Towards evaluating the
article.
REFERENCES
[1] Mofeed T. Rashid, "Modeling Of Self-Organization Fish
School System By Neural Network System," Basrah
Journal for Engineering Science, vol. 15, no. 1, pp. 14-19,
2015.
[2] I. Goodfellow, Jonathon Shlens, Christian Szegedy,
"Explaining and harnessing adversarial examples," 2014.
[3] R. Huang, B. Xu, D. Schuurmans, and C. J. Szepesvári,
"Learning with a strong adversary," CoRR, 2015.
[4] Harini Kannan, Alexey Kurakin, Ian Goodfellow,
"Adversarial logit pairing," CoRR, Vol. abs/1803.06373,
2018.
[5] Alexey Kurakin, Ian Goodfellow, Samy Bengio,
"Adversarial machine learning at scale," Computer Vision
and Pattern Recognition, 2016.
[6] A. Bharati, R. Singh, M. Vatsa, K. W. Bowyer, and
Security, "Detecting facial retouching using supervised
deep learning," IEEE Transactions on Information
Forensics and Security, vol. 11, no. 9, pp. 1903-1913,
2016.
[7] Christian Szegedy, Wojciech Zaremba, Ilya Sutskever,
Joan Bruna, Dumitru Erhan, Ian Goodfellow, Rob Fergus,
"Intriguing properties of neural networks," Computer
Vision and Pattern Recognition, 2013.
[8] A. Agarwal, R. Singh, M. Vatsa, and N. Ratha, "Are
image-agnostic universal adversarial perturbations for
face recognition difficult to detect?," in 2018 IEEE 9th
International Conference on Biometrics Theory,
Applications and Systems (BTAS), pp. 1-7, 2018.
[9] Y. Liu, S. Mao, X. Mei, T. Yang, and X. Zhao,
"Sensitivity of Adversarial Perturbation in Fast Gradient
Sign Method," in 2019 IEEE Symposium Series on
Computational Intelligence (SSCI), pp. 433-436, 2019.
[10] S. M. Moosavi-Dezfooli, A. Fawzi, and P. Frossard,
"Deepfool: a simple and accurate method to fool deep
neural networks," in Proceedings of the IEEE conference
on computer vision and pattern recognition, pp.
2574-2582, 2016.
[11] J. Xue, Y. Yang, and D. Jing, "Deceiving Face
Recognition Neural Network with Samples Generated by
Deepfool," in Journal of Physics: Conference Series, vol.
1302, no. 2, 2019.
[12] Aleksander Madry, Aleksandar Makelov, Ludwig
Schmidt, Dimitris Tsipras, Adrian Vladu, "Towards deep
learning models resistant to adversarial attacks,"
arXiv:1706.06083, 2017.
[13] A. Goel, A. Agarwal, M. Vatsa, R. Singh, and N. K.
Ratha, "DNDNet: Reconfiguring CNN for adversarial
robustness," in Proceedings of the IEEE/CVF Conference
on Computer Vision and Pattern Recognition Workshops,
pp. 22-23, 2020.
robustness of neural networks," in 2017 ieee symposium
on security and privacy (sp), pp. 39-57, 2017.
[15] N. Papernot, P. McDaniel, X. Wu, S. Jha, and A.
Swami, "Distillation as a defense to adversarial
perturbations against deep neural networks," in 2016 IEEE
symposium on security and privacy (SP), pp. 582-597,
2016.
[16] D. Deb, J. Zhang, and A. K. Jain, "Advfaces:
Adversarial face synthesis," in 2020 IEEE International
Joint Conference on Biometrics (IJCB), pp. 1-10, 2020.
[17] M. Cisse, P. Bojanowski, E. Grave, Y. Dauphin, and N.
Usunier, "Parseval networks: Improving robustness to
adversarial examples," in International Conference on
Machine Learning, pp. 854-863, 2017.
[18] A. Dubey, L. Maaten, Z. Yalniz, Y. Li, and D. Mahajan,
"Defense against adversarial images using web-scale
nearest-neighbor search," in Proceedings of the
IEEE/CVF Conference on Computer Vision and Pattern
Recognition, pp. 8767-8776, 2019.
[19] G. B. Huang, M. Mattar, T. Berg, and E.
Learned-Miller, "Labeled faces in the wild: A database
forstudying face recognition in unconstrained
environments," in Workshop on faces in'Real-Life'Images:
detection, alignment, and recognition, 2008.