Artificial Intelligence in Cybersecurity: Techniques, Limitations, and Research Directions
- 1DHA Suffa University
Abstract
Artificial intelligence (AI) is increasingly used to support cybersecurity tasks such as network
intrusion detection, malware analysis, threat intelligence, and security-operations workflows. At the
same time, AI-enabled systems introduce risks related to model opacity, adversarial manipulation,
privacy, distribution shift, and misuse of generative models. This narrative review organizes the topic
into four connected areas: AI-based detection, explainable AI (XAI), adaptive threat intelligence, and
generative AI and large language models (LLMs). Across these areas, the central engineering
challenge is not only to detect malicious activity, but to produce reliable, interpretable, and operationally
useful outputs under changing conditions. The review highlights recurring limitations in evaluation
realism, explainability, adaptation to evolving threats, and human oversight. It proposes a practical
research agenda focused on reproducible benchmarking, robustness testing, human-in-the-loop
response, privacy-aware data practices, and transparent reporting. Because this manuscript is a
narrative review rather than a systematic review, it does not claim exhaustive coverage of the literature.
A future version should document a reproducible search and screening protocol and verify all
bibliographic records before journal submission
Related
- A hybrid structural and artificial intelligence approach for cybersecurity situational awareness among high school students
- Integrating artificial intelligence and molecular simulation for peptide discovery: limitations, validation and decision-centered workflows
- Low-Dose CT in the Age of Artificial Intelligence: Techniques, Evidence, and Clinical Impact
- Bridging the Translational Gap in Artificial Intelligence for Otology and Neurotology: Clinical Readiness, Limitations, and Research Priorities
- Artificial Intelligence in Bioengineering: Innovations, Challenges, and Future Directions: A Narrative Review
BibTeX
@misc{shah2026artificial,
title = {{Artificial Intelligence in Cybersecurity: Techniques, Limitations, and Research Directions}},
author = {Syed Tabish Shah},
howpublished = {Zenodo},
year = {2026},
month = oct,
doi = {10.5281/zenodo.23450799},
url = {https://zenodo.org/records/23450799},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Artificial Intelligence in Cybersecurity: Techniques, Limitations, and Research Directions
AU - Syed Tabish Shah
PY - 2026
DA - 2026/10/18
PB - Zenodo
DO - 10.5281/zenodo.23450799
UR - https://zenodo.org/records/23450799
AB - Artificial intelligence (AI) is increasingly used to support cybersecurity tasks such as network intrusion detection, malware analysis, threat intelligence, and security-operations workflows. At the same time, AI-enabled systems introduce risks related to model opacity, adversarial manipulation, privacy, distribution shift, and misuse of generative models. This narrative review organizes the topic into four connected areas: AI-based detection, explainable AI (XAI), adaptive threat intelligence, and generative AI and large language models (LLMs). Across these areas, the central engineering challenge is not only to detect malicious activity, but to produce reliable, interpretable, and operationally useful outputs under changing conditions. The review highlights recurring limitations in evaluation realism, explainability, adaptation to evolving threats, and human oversight. It proposes a practical research agenda focused on reproducible benchmarking, robustness testing, human-in-the-loop response, privacy-aware data practices, and transparent reporting. Because this manuscript is a narrative review rather than a systematic review, it does not claim exhaustive coverage of the literature. A future version should document a reproducible search and screening protocol and verify all bibliographic records before journal submission
ER -