Robustness of Neural Networks: Adversarial Attacks and Defenses
International Journal on Advanced Electrical and Computer Engineering · 2025-04-15 · 13 (1) · 7-13
DOI: 10.65521/ijaece.v13i1.84 ↗At a glance
Journal article in International Journal on Advanced Electrical and Computer Engineering, published online on 2025-04-15. Written by Akash Verma and 1 co-authors.
Abstract (original language)
Quantum Machine Learning (QML) is an emerging interdisciplinary field that integrates quantum computing with classical machine learning techniques to enhance computational efficiency and solve complex problems beyond the capabilities of classical systems. This paper explores fundamental QML algorithms, including quantum-enhanced data processing, quantum neural networks, and quantum support vector machines. We discuss how quantum speedup can be achieved through quantum parallelism and entanglement, leading to improvements in optimization and data classification tasks. Additionally, we highlight applications of QML in areas such as drug discovery, financial modeling, and cryptography. While current quantum hardware imposes limitations, ongoing advancements in quantum algorithms and error correction techniques suggest a promising future for QML. We conclude with a discussion on the challenges and future directions in the field, emphasizing the need for hybrid quantum-classical approaches and scalable quantum hardware.
Cite
APA
Verma, A., & Gonzalez, M. (2025). Robustness of Neural Networks: Adversarial Attacks and Defenses. International Journal on Advanced Electrical and Computer Engineering, 13(1), 7-13. https://doi.org/10.65521/ijaece.v13i1.84
Vancouver
Verma A, Gonzalez M. Robustness of Neural Networks: Adversarial Attacks and Defenses. International Journal on Advanced Electrical and Computer Engineering. 2025;13(1):7-13. doi:10.65521/ijaece.v13i1.84
BibTeX
@article{Verma2025,
author = {Verma, Akash and Gonzalez, Maria},
title = {Robustness of Neural Networks: Adversarial Attacks and Defenses},
journal = {International Journal on Advanced Electrical and Computer Engineering},
year = {2025},
volume = {13},
number = {1},
pages = {7--13},
doi = {10.65521/ijaece.v13i1.84}
}
EUVIMED