◆ International Journal of Technology2026-07-31· Adversarial system
Adaptive Gradient Shielding for Consistent Defense Against Adversarial Attacks in Deep Learning
Qais S. Qassim, Wilfred B. N. Reginal, Dilwar I. Mazunder, Samuel B. Sangeetha, Yuvaraj Natarajan, Arshath R. Rajan
原始摘要（英文原文）· Original abstract
Deep learning models are highly vulnerable to adversarial perturbations, posing serious risks in critical domains such as healthcare, autonomous systems, and cybersecurity. This has motivated the need for robust defenses that maintain reliabilit