MétaCan
Menu
Back to cohort
Record W4413201737 · doi:10.5539/cis.v18n2p1

Neuro-Symbolic Reasoning for Cyber Compliance Violation Detection

2025· article· en· W4413201737 on OpenAlexvenueno aff
Kutub Thakur

Bibliographic record

VenueComputer and Information Science · 2025
Typearticle
Languageen
FieldComputer Science
TopicNetwork Security and Intrusion Detection
Canadian institutionsnot available
Fundersnot available
KeywordsInterpretabilityComputer scienceScalabilityConsistency (knowledge bases)Artificial intelligenceMachine learningArtificial neural networkTransparency (behavior)Computer securityDatabase

Abstract

fetched live from OpenAlex

This paper presents a neuro-symbolic framework for detecting cyber compliance violations by integrating deep neural networks with symbolic rule-based reasoning. Traditional machine learning models, while effective in identifying complex patterns, often lack interpretability, limiting their use in regulated domains where explainability is essential. Conversely, symbolic systems offer transparency but are rigid and difficult to scale. Our approach unifies these paradigms by jointly optimizing predictive performance and symbolic rule consistency. Compliance knowledge is encoded as Boolean constraints and incorporated during training as a regularization objective. The model fuses neural embeddings with rule satisfaction signals to improve both accuracy and interpretability. Evaluated on real-world cybersecurity datasets, our method achieves a 99.1% accuracy, 0.96 F1-score, and a reduced false positive rate, outperforming existing baselines. The framework also provides interpretable justifications by identifying violated rules, enhancing trust and auditability. These results demonstrate the feasibility and value of neuro-symbolic systems in scalable, explainable compliance monitoring.

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 distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.934
Threshold uncertainty score0.704

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0010.009
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.014
GPT teacher head0.258
Teacher spread0.244 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueComputer and Information ScienceSame topicNetwork Security and Intrusion DetectionFrench-language works237,207