Deep Learning in Cybersecurity: Applications, Challenges, and Future Prospects DOI

Levina Tukaram

International Journal of Innovations in Science Engineering and Management., Journal Year: 2025, Volume and Issue: unknown, P. 27 - 33

Published: April 12, 2025

Cybersecurity risks are heightened by the quick proliferation of smart things and growing frequency severity intrusions. primarily guards against external assaults on data, software, hardware that part a system with an active internet connection. is used organizations to guard unwanted access their records systems. In this article review various literature’s study deep learning in cybersecurity. Additionally, explore challenges, application future prospects Cybersecurity. It concluded plays crucial role cybersecurity enhancing intrusion detection, malware classification, anomaly detection. Techniques like SMOTE address class imbalance, while models such as CatBoost XGBoost outperform identifying cyber threats. Challenges include handling untidy, hierarchical optimizing model parameters, balancing accuracy training time. Future advancements will focus improving detection performance, securing neural networks adversarial attacks, for resource-constrained environments. Integrating multiple parallel can enhance efficiency, making vital tool IoT addressing evolving

Language: Английский

Cybercrime through the public lens: a longitudinal analysis DOI Creative Commons
Krishnashree Achuthan,

Sugandh Khobragade,

Robin M. Kowalski

et al.

Humanities and Social Sciences Communications, Journal Year: 2025, Volume and Issue: 12(1)

Published: March 1, 2025

Language: Английский

Citations

0
Business Intelligence Threat Detection Through Advanced AI and ML DOI
Faisal Aburub, Ammar Almomani

IGI Global eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 377 - 398

Published: April 11, 2025

Business intelligence (BI) systems are integral to strategic and operational decision-making in contemporary data-driven organizations. As these platforms accumulate increasingly large intricate datasets, they become prime targets for sophisticated cyber threats. This chapter examines how artificial (AI) machine learning (ML) methods fortify the security of BI environments mitigate escalating incidence advanced attacks. The discussion reviews BI's evolution from static reporting functionalities dynamic, real-time analytics, a transformation that parallels increased vulnerabilities novel adversarial tactics. It then analyzes theoretical foundations AI- ML-based threat detection, encompassing anomaly defenses, explainable AI (XAI).

Language: Английский

Citations

0
AI for Healthcare Security: The Intersection of Innovation and Resilience DOI
Ankur Shukla

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 109 - 127

Published: Jan. 1, 2025

Language: Английский

Citations

0
Advancing Cybersecurity Through Machine Learning: A Scientometric Analysis of Global Research Trends and Influential Contributions DOI Creative Commons
Kamran Razzaq, Mahmood Shah

Journal of Cybersecurity and Privacy, Journal Year: 2025, Volume and Issue: 5(2), P. 12 - 12

Published: March 22, 2025

Implementing machine learning is imperative for enhancing advanced cybersecurity practices globally. The current landscape needs further investigation into the potential impasse. This scientometric study aims to comprehensively analyse patterns and key contributions at nexus of learning. analysis examines publication trends, citation analysis, intensive research networks discover authors, significant organisations, major countries, emerging areas. search was conducted on Scopus database, 3712 final documents were selected after a thorough screening from January 2016 2025. VOSviewer tool used map visualise co-authorship networks, enabling discovery patterns, top contributors, hot topics in domain. findings uncovered substantial growth publications bridging with deep learning, involving 2865 authors across 160 institutions 114 countries. Saudi Arabia emerged as contributing nation flaunting high productivity. IEEE Sensors are sources instrumental producing interdisciplinary research. Iqbal H. Sarker N. Moustafa notable 17 16 each. emphasises significance global partnerships multidisciplinary posture identifying areas future studies. highlights its importance by guiding policymakers practitioners develop learning-based strategies.

Language: Английский

Citations

0
Deep Learning in Cybersecurity: Applications, Challenges, and Future Prospects DOI

Levina Tukaram

International Journal of Innovations in Science Engineering and Management., Journal Year: 2025, Volume and Issue: unknown, P. 27 - 33

Published: April 12, 2025

Cybersecurity risks are heightened by the quick proliferation of smart things and growing frequency severity intrusions. primarily guards against external assaults on data, software, hardware that part a system with an active internet connection. is used organizations to guard unwanted access their records systems. In this article review various literature’s study deep learning in cybersecurity. Additionally, explore challenges, application future prospects Cybersecurity. It concluded plays crucial role cybersecurity enhancing intrusion detection, malware classification, anomaly detection. Techniques like SMOTE address class imbalance, while models such as CatBoost XGBoost outperform identifying cyber threats. Challenges include handling untidy, hierarchical optimizing model parameters, balancing accuracy training time. Future advancements will focus improving detection performance, securing neural networks adversarial attacks, for resource-constrained environments. Integrating multiple parallel can enhance efficiency, making vital tool IoT addressing evolving

Language: Английский

Citations

0