InfoSecPilot: Navigating the Complex Landscape of Information Security with an AI-Powered Knowledge Management Chatbot
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This research investigates the development and implementation of an AI-powered conversational agent utilizing large language models (LLMs) to enhance knowledge management capabilities for information security professionals. The study employed systematic prompt engineering methodologies and structured technology validation protocols to assess chatbot performance across multiple evaluation frameworks, including user satisfaction metrics, Cohen's Kappa inter-rater reliability analysis, and Confusion Matrix statistical validation. Empirical results demonstrate substantial concordance between AI-generated responses and subject matter expert assessments, with statistically significant accuracy rates and high user satisfaction scores. The findings establish the technical feasibility and practical utility of generative AI systems as sophisticated decision-support tools within information security practice domains. This investigation contributes empirical evidence supporting the integration of AI-assisted technologies in professional workflows, demonstrating measurable improvements in knowledge accessibility and evidence-based decision-making processes. The research represents a significant advancement in applying generative artificial intelligence to specialized professional contexts, providing foundational insights for broader adoption of AI-enhanced knowledge management systems in information security practice.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.003 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it