Artificial Intelligence and Machine Learning in Cybersecurity: Impact on Threat Detection and Incident Response

The increasing sophistication, volume, and velocity of cyber threats have rendered traditional rulebased and signature-driven cybersecurity mechanisms increasingly inadequate. Modern attacks, such as zero-day exploits, ransomware, advanced persistent threats, and insider attacks, operate with high adaptability and stealth, overwhelming conventional security systems and delaying effective incident response. In response, Artificial Intelligence (AI) and Machine Learning (ML) have emerged as critical enablers of intelligent, adaptive, and automated cybersecurity defenses. This study systematically reviews existing literature to examine the impact of AI and ML on cybersecurity, with a specific focus on threat detection and incident response. Adopting a Systematic Literature Review (SLR) methodology, the study synthesizes peer-reviewed academic articles and high-quality industry reports published between 2018 and 2024, sourced from major databases including Scopus, IEEE Xplore, Web of Science, and ScienceDirect. The review analyzes how supervised, unsupervised, reinforcement learning, and deep learning techniques are applied across cybersecurity domains such as intrusion detection, malware classification, behavioural analytics, and automated incident response. The findings reveal that AI-driven cybersecurity systems significantly enhance detection accuracy, reduce false positives, and substantially decrease mean time to detection and response. Deep learning models demonstrate superior performance in identifying complex and previously unseen attack patterns, while reinforcement learning supports adaptive policy optimization for dynamic threat environments. However, the review also identifies persistent challenges related to data quality, model interpretability, adversarial attacks, ethical considerations, and governance constraints. This study, therefore, advances the conceptual understanding of AI as both an adaptive learning mechanism and a systemic component within security architectures; and contributes to cybersecurity scholarship by consolidating fragmented evidence, and offering strategic implications for organizations seeking resilient, ethical, and scalable AI-driven cybersecurity solutions.

Authors

Institutions

Publication Details

Journal
INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN
Published
2026-11-16
DOI
https://doi.org/10.56201/ijcsmt.vol.10.no6.2024.pg181.192
Citations
2
Primary Topic
Network Security and Intrusion Detection
Type
article
Field-Weighted Citation Impact
1.67
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Artificial Intelligence and Machine Learning in Cybersecurity: Impact on Threat Detection and Incident Response

Israel Boafo Bansah
2 citations
INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN
Network Security and Intrusion Detection
1.67
article

Artificial Intelligence and Machine Learning in Cybersecurity: Impact on Threat Detection and Incident Response

Israel Boafo Bansah
article en
2 citations

Abstract

The increasing sophistication, volume, and velocity of cyber threats have rendered traditional rulebased and signature-driven cybersecurity mechanisms increasingly inadequate. Modern attacks, such as zero-day exploits, ransomware, advanced persistent threats, and insider attacks, operate with high adaptability and stealth, overwhelming conventional security systems and delaying effective incident response. In response, Artificial Intelligence (AI) and Machine Learning (ML) have emerged as critical enablers of intelligent, adaptive, and automated cybersecurity defenses. This study systematically reviews existing literature to examine the impact of AI and ML on cybersecurity, with a specific focus on threat detection and incident response. Adopting a Systematic Literature Review (SLR) methodology, the study synthesizes peer-reviewed academic articles and high-quality industry reports published between 2018 and 2024, sourced from major databases including Scopus, IEEE Xplore, Web of Science, and ScienceDirect. The review analyzes how supervised, unsupervised, reinforcement learning, and deep learning techniques are applied across cybersecurity domains such as intrusion detection, malware classification, behavioural analytics, and automated incident response. The findings reveal that AI-driven cybersecurity systems significantly enhance detection accuracy, reduce false positives, and substantially decrease mean time to detection and response. Deep learning models demonstrate superior performance in identifying complex and previously unseen attack patterns, while reinforcement learning supports adaptive policy optimization for dynamic threat environments. However, the review also identifies persistent challenges related to data quality, model interpretability, adversarial attacks, ethical considerations, and governance constraints. This study, therefore, advances the conceptual understanding of AI as both an adaptive learning mechanism and a systemic component within security architectures; and contributes to cybersecurity scholarship by consolidating fragmented evidence, and offering strategic implications for organizations seeking resilient, ethical, and scalable AI-driven cybersecurity solutions.

INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN
Webster University (US)
Openalex Percentile: Top 19%
Network Security and Intrusion Detection
1.67
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon