Home / Current Issue / Paper 1718467
AI-Assisted Vulnerability Discovery and Reporting: Reliability Challenges, Security Risks, and Future Directions
Subject area: Science,Engineering and Technology · Area of research: Cyber Security
DOI: https://doi.org/10.64388/IREV9I11-1718467
Abstract
In the contemporary world of cyber security, AI plays a significant part and is extensively recognized in finding and reporting vulnerabilities. Due to recent advancement in Machine Learning (ML), Deep Learning (DL) and Large Language Models (LLMs), various automated tools for finding vulnerabilities in software, reporting security bugs, and suggest patches for them are currently available. This work aims at identifying existing literature on AI assisted vulnerability detection and reporting system with a special focus on their security and reliability issue. Works from year 2023 to 2026 are reviewed and analyzed with categorizing them on the basis of their aim, techniques employed, merits and demerits. From our analysis, key reliability issues identified are; false positives, false negatives, hallucinations, inaccurate severity rating, and complexity in interpretations whereas the major security threats encountered were prompt injection attacks, adversarial manipulation of input data, poisoning data and leaking sensitive information. Based on the findings of this study, it is concluded that while there are numerous benefits to the AI assisted cyber security system, humans can never be out of the loop and supervision and interpretation of security flaws based on credibility cannot be disregarded in practical applications. We highlight some major challenges in current approaches along with several future research direction in order to achieve a dependable and secure AI-assisted vulnerability assessment system.
Keywords
Artificial Intelligence, Cyber Security, Vulnerability Discovery, Vulnerability Reporting, Trustworthy AI, Large Language Models.
References
[1] S. Shimmi, H. Okhravi, and M. Rahimi, “AI- Based Software Vulnerability Detection: A Systematic Literature Review,” arXiv preprint arXiv:2506.10280, 2025.
[2] A. Malkawi et al., “AI-Powered Vulnerability Detection and Patch Management in Cybersecurity: A Systematic Review of Techniques, Challenges and Emerging Trends,” AI Journal, vol. 8, no. 1, 2026.
[3] M. Mirtaheri et al., “Cybersecurity in the Age of Generative AI: A Systematic Review,” Future Generation Computer Systems, 2025.
[4] M. A. Ferrag, “Generative AI in Cybersecurity: A Comprehensive Review of Large Language Models Applications and Vulnerabilities,” Array, vol. 25, 2025.
[5] A. Tumpa et al., “Generative AI in Cybersecurity: A Systematic Literature Review and Meta-Analysis,” Preprints, 2026.
[6] D. Nott, “Organizational Adaptation to Generative AI in Cybersecurity: A Systematic Review,” arXiv preprint, 2025.
[7] B. Yiğit and M. Alkan, “Review of Generative AI Methods in Cybersecurity,” Array, vol. 26, 2026.
[8] M. Ibrar et al., “Generative AI: A Double- Edged Sword in the Cyber Threat Landscape,” Artificial Intelligence Review, 2025.
[9] M. Uddin et al., “Generative AI Revolution in Cybersecurity: Opportunities and Challenges,” Artificial Intelligence Review, 2025.
[10] P. Kaniewski et al., “A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models,” arXiv preprint arXiv:2507.22659, 2025.
[11] M. Naseer et al., “A Systematic Literature Review for Transformer-Based Software Vulnerability Detection,” arXiv preprint arXiv:2604.24822, 2026.
[12] Vincent Tamaramiebi Daniel, Biralatei Fawei, “A Systematic Review of AI-Driven Automated Software Vulnerability Detection Systems,” International Journal of Computer Science and Mathematical Theory, 2025.
[13] M. Lezzi et al., “A Systematic Literature Review on AI -Based Cybersecurity,” Cybersecurity, vol. 5, no. 4, 2025.
How to cite this paper
@article{1718467,
author = {Shaik Mohammad Yasin, Kalisetti Venkatesh, Heema Chetri},
title = {AI-Assisted Vulnerability Discovery and Reporting: Reliability Challenges, Security Risks, and Future Directions},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {4779-4787},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1718467.pdf},
abstract = {In the contemporary world of cyber security, AI plays a significant part and is extensively recognized in finding and reporting vulnerabilities. Due to recent advancement in Machine Learning (ML), Deep Learning (DL) and Large Language Models (LLMs), various automated tools for finding vulnerabilities in software, reporting security bugs, and suggest patches for them are currently available. This work aims at identifying existing literature on AI assisted vulnerability detection and reporting system with a special focus on their security and reliability issue. Works from year 2023 to 2026 are reviewed and analyzed with categorizing them on the basis of their aim, techniques employed, merits and demerits. From our analysis, key reliability issues identified are; false positives, false negatives, hallucinations, inaccurate severity rating, and complexity in interpretations whereas the major security threats encountered were prompt injection attacks, adversarial manipulation of input data, poisoning data and leaking sensitive information. Based on the findings of this study, it is concluded that while there are numerous benefits to the AI assisted cyber security system, humans can never be out of the loop and supervision and interpretation of security flaws based on credibility cannot be disregarded in practical applications. We highlight some major challenges in current approaches along with several future research direction in order to achieve a dependable and secure AI-assisted vulnerability assessment system.},
keywords = {Artificial Intelligence, Cyber Security, Vulnerability Discovery, Vulnerability Reporting, Trustworthy AI, Large Language Models.},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1718467}
}