Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM67508
Volume:
10 |
9 |
Sep 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Cyber Security
Chikitsak Samuha's Patkar Varde College
Artificial intelligence and machine learning models are being leveraged to automate preexisting verification, testing, and security analysis tools, with substantial benefits for operational efficiency but at the cost of introducing severe uncertainty in final results. Notably, automated wrappers often raise false positives (Type I errors) due to excessively strict feature thresholds or exhibit false negatives (Type II errors) by ignoring potential underlying issues in complex or obfuscated situations. This paper looks at where uncertainty in results comes from in AI-driven automation tools, using multimodal verification and semantic assessment. It provides a way to categorize automation confusion and explains how false positives and overlooked vulnerabilities can affect operations. The paper concludes by discussing a hybrid evaluation framework which seeks to address these concerns.
KEYWORDS
AI automation tools can help reduce manual work by improving existing tools, but they also create uncertainty about results because of incorrect positive findings and overlooked weaknesses. By identifying these risks, understanding how they affect operations, and using a mixed approach that combines tool data with careful checks, organizations can take advantage of automation's speed while ensuring strong verification standards. In the end, matching machine speed with people checking things makes sure big mistakes are reduced. This ongoing adjusting lets teams keep systems working well without getting tired of warnings or just believing what machines say.
[1] M. S. Akbar, "Beyond Detection: Designing AI-Resilient Assessments with Automated Feedback Tool to Foster Critical Thinking," arXiv preprint arXiv:2503.23622, 2025. [Online]. Available: https://arxiv.org/abs/2503.23622 [2] V. Garousi et al., "AI-powered software testing tools: A systematic review and empirical assessment of their features and limitations," arXiv preprint arXiv:2409.00411, 2024. [Online]. Available: https://arxiv.org/abs/2409.00411 [3] M. S. Akbar et al., "Uncertainty Analysis in AI-Driven Automation and Verification Wrappers," Social Science Research Network (SSRN) Electronic Journal, SSRN Abstract: 7138178, 2026. [Online]. Available: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7138178
Publication Date
9/26/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...