A bibliometric study toward quantitative research assessment of security of machine learning DOI
Anum Paracha, Junaid Arshad

Information Discovery and Delivery, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 30, 2024

Purpose Advances in machine learning (ML) have made significant contributions to the development of intelligent and autonomous systems leading concerns about resilience such against cyberattacks. This paper aims report findings from a quantitative analysis literature within ML security assess current research trends security. Design/methodology/approach The study focuses on statistical published between 2000 2023, providing targeting authors, countries interdisciplinary studies organizations. reports existing surveys comparison publications attacks its in-demand Furthermore, an in-depth keywords, citations collaboration is presented facilitate deeper this literature. Findings Trends identified 2021 2022 highlight increase focus adversarial – 40\% more compared 2020–2022 with than 90\% journals. has also respect citations, keywords analysis, annual publications, co-author geographical highlighting China USA as highest count Biggio B. researcher collaborative strength 143 co-authors which pollination ideas knowledge. Keyword highlighted deep computer vision most common domains for due potential perturb images whilst being challenging identify issues because complex architecture. Originality/value identifies trends, author open challenges that can further domain.

Language: Английский

Disruptive Attacks on Artificial Neural Networks: A Systematic Review of Attack Techniques, Detection Methods, and Protection Strategies DOI Creative Commons
Talal Bonny, Talal Bonny, Maher Alrahhal

et al.

Intelligent Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 200529 - 200529

Published: April 1, 2025

Language: Английский

Citations

0

A bibliometric study toward quantitative research assessment of security of machine learning DOI
Anum Paracha, Junaid Arshad

Information Discovery and Delivery, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 30, 2024

Purpose Advances in machine learning (ML) have made significant contributions to the development of intelligent and autonomous systems leading concerns about resilience such against cyberattacks. This paper aims report findings from a quantitative analysis literature within ML security assess current research trends security. Design/methodology/approach The study focuses on statistical published between 2000 2023, providing targeting authors, countries interdisciplinary studies organizations. reports existing surveys comparison publications attacks its in-demand Furthermore, an in-depth keywords, citations collaboration is presented facilitate deeper this literature. Findings Trends identified 2021 2022 highlight increase focus adversarial – 40\% more compared 2020–2022 with than 90\% journals. has also respect citations, keywords analysis, annual publications, co-author geographical highlighting China USA as highest count Biggio B. researcher collaborative strength 143 co-authors which pollination ideas knowledge. Keyword highlighted deep computer vision most common domains for due potential perturb images whilst being challenging identify issues because complex architecture. Originality/value identifies trends, author open challenges that can further domain.

Language: Английский

Citations

0