The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
A Comparative Study on Adversarial Noise Generation for Single Image Classification
Abstract
With the rise of neural network-based classifiers, it is evident that these algorithms are here to stay. Even though various algorithms have been developed, these classifiers still remain vulnerable to misclassification attacks. This article outlines a new noise layer attack based on adversarial learning and compares the proposed method to other such attacking methodologies like Fast Gradient Sign Method, Jacobian-Based Saliency Map Algorithm and DeepFool. This work deals with comparing these algorithms for the use case of single image classification and provides a detailed analysis of how each algorithm compares to each other.
Related Content
Li Liao.
© 2024.
16 pages.
|
Shuqin Zhang, Peiyu Shi, Tianhui Du, Xinyu Su, Yunfei Han.
© 2024.
27 pages.
|
Jinming Zhou, Yuanyuan Zhan, Sibo Chen.
© 2024.
29 pages.
|
G. Manikandan, Reuel Samuel Sam, Steven Frederick Gilbert, Karthik Srikanth.
© 2024.
16 pages.
|
Liangqun Yang.
© 2024.
17 pages.
|
V. Shanmugarajeshwari, M. Ilayaraja.
© 2024.
22 pages.
|
Kaisheng Liu.
© 2024.
21 pages.
|
|
|