The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Enhancing Machine Learning Security With Robust Discretization-Based Defenses Against Adversarial Attacks
Abstract
Machine learning (ML) models have security weaknesses, as small input perturbations cause misclassifications, risking healthcare, finance, and autonomous systems. A defense strategy using discrete representation transformation of continuous features enhances model resistance to adversarial attacks. A comparative analysis of discretization methods—quantization, binning, and entropy-based partitioning—applies to ML models like decision trees and deep neural networks. Our defense is tested on adversarial datasets (ImageNet-A, MNIST Adversarial, CIFAR-10 Adversarial) against FGSM, PGD, and CW attacks. Performance evaluation considers accuracy, robustness, adversarial transferability, and computational efficiency. Results show discretization reduces misclassification by 30% while maintaining strong prediction performance. Our research highlights its low cost compared to adversarial training, ensuring scalability. Future work explores adaptive and hybrid discretization to enhance ML security and optimize robustness-efficiency trade-offs.
Related Content
|
Frederic Andres.
© 2027.
14 pages.
|
|
Kalsoom Safdar, Khairul Najmy Abdul Rani, Mohd Aminudin Jamlos, Siti Julia Rosli, Muhammad Usman Younus, Zanab Safdar.
© 2027.
27 pages.
|
|
Bani Adam, Binastya Anggara Sekti, Muhammad Adi Zacky Zahran.
© 2027.
24 pages.
|
|
Swetha Margaret T. A., Renuka Devi D..
© 2027.
31 pages.
|
|
Maurice Saluschke, Michael Schulz.
© 2027.
30 pages.
|
|
Mirjam Sepesy Maučec, Gregor Donaj.
© 2027.
16 pages.
|
|
Jorge A. Ruiz-Vanoye, Ocotlan Diaz-Parra, Ricardo A. Barrera-Cámara, Alejandro Fuentes-Penna, Francisco R. Trejo-Macotela, Jaime Aguilar-Ortiz, Eric Simancas-Acevedo.
© 2027.
21 pages.
|
|
|