Enhancing Cybersecurity Threat Detection with Counterfactual Reasoning: A 'What-If' Ontology Approach Using Large Language Models
Bibliographic record
Abstract
This paper proposes a novel approach to enhancing cybersecurity threat detection by integrating counterfactual reasoning with large language models (LLMs) through a structured "what-if" ontology. Traditional AI-based systems often function as black boxes, identifying threats without offering causal explanations or scenario reasoning. Our framework enables LLMs to simulate hypothetical attack scenarios and assess alternative outcomes, thereby improving detection accuracy and interpretability. Grounded in the TOVE ontology engineering methodology, the system aims to formalize key cybersecurity entities, causal relations, and counterfactual conditions using languages like OWL and SWRL. We evaluate the framework based on metrics such as detection accuracy, narrative quality, and reasoning robustness. By unifying theoretical foundations from causal reasoning, scenario planning, and facets of explainable AI, our ontology serves as a semantic backbone for LLM-guided analysis. This work contributes a proactive, explainable, and extensible model for anticipating cyber threats and guiding defensive strategies, with implications for future research and implementation in intelligent threat detection systems.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.004 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.004 |
| Scholarly communication | 0.005 | 0.013 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".