CINN-UTLC: A Computationally Intelligent Neural Network-Based Unsupervised Transfer Learning Algorithm for Ransomware Detection
Bibliographic record
Abstract
The relentless evolution of ransomware demands detection frameworks that adapt to novel variants and minimize reliance on labelled data.Existing methods often suffer from distribution shifts, limited generalizability, and opaque decision-making.This study introduces CINN-UTLC, a computationally intelligent neural network-based unsupervised transfer learning algorithm that integrates domain adaptation, hybrid feature extraction, and explainable clustering for ransomware detection.By combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) models, CINN-UTLC captures static features (e.g., file entropy, headers) and dynamic behaviours (e.g., API call sequences) while aligning source (benign) and target (unlabelled) domains via Geometric Alignment Clustering (GAC).The framework employs SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) to interpret feature contributions, ensuring transparency in clustering decisions.CINN-UTLC achieves a 98% detection rate, 2.5% false positive rate, and AUC of 0.94, outperforming benchmarks like UNVEIL (AUC=0.78)and deep learning methods (AUC=0.73).Clustering metrics (Silhouette Score: 0.80-0.86;Adjusted Rand Index: 0.87-0.93)confirm robust separation of ransomware families, including zero-day variants.The algorithm's unsupervised transfer learning capability enables detection of unknown ransomware through behavioural anomalies, even without labelled target data.By addressing domain shifts, reducing false positives, and offering explainable insights, CINN-UTLC sets a new standard for adaptive cybersecurity frameworks, bridging critical gaps in ransomware resilience and proactive threat mitigation.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".