Adversarial Attacks in Machine Learning: Key Insights and Defense Approaches

YL Khaleel, MA Habeeb… - Applied Data Science and …, 2024 - mesopotamian.press
There is a considerable threat present in genres such as machine learning due to
adversarial attacks which include purposely feeding the system with data that will alter the …

[HTML][HTML] Similarity-driven adversarial testing of neural networks

K Filus, J Domańska - Knowledge-Based Systems, 2024 - Elsevier
Abstract Although Convolutional Neural Networks (CNNs) are among the most important
algorithms of computer vision and the artificial intelligence-based systems, they are …

Decreasing adversarial transferability using gradient information of attack paths

M Xu, L Liu, P Xia, Z Li, B Li - Applied Soft Computing, 2025 - Elsevier
Adversarial transferability is an intriguing yet dangerous property of deep neural networks
(DNNs), enabling the potential for black-box adversarial attacks. To better safeguard DNN …

Efficient Large Margin Adversarial Training Based on Decision Boundaries for Adversarial Robustness

M Xu, Z Li, L Liu, B Li - Available at SSRN 5031724 - papers.ssrn.com
Recent literature has evidence that adversarial training and its related optimizing methods
have achieved significant results in improving the adversarial robustness of deep neural …