Black-box Adversarial Transferability: An Empirical Study in Cybersecurity Perspective

• Published in: arXiv.org
• Main Authors: Khushnaseeb Roshan, Zafar, Aasim
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 15.04.2024
• Subjects: Artificial intelligence; Black boxes; Classification; Computer Science - Cryptography and Security; Computer Science - Learning; Cybersecurity; Deep learning; Machine learning; Performance measurement; Perturbation

The rapid advancement of artificial intelligence within the realm of cybersecurity raises significant security concerns. The vulnerability of deep learning models in adversarial attacks is one of the major issues. In adversarial machine learning, malicious users try to fool the deep learning model b...