Sharma, Priynka and Chaudhary, Kaylash C. (2024) An Advanced Comparative Study of Ransomware Anomaly Detection Techniques Through Optimized Hyperparameters. In: Artificial Intelligence and Sustainable Computing. Algorithms for Intelligent Systems . Springer Nature, Singapore, pp. 429-445. ISBN 978-981-97-0327-2_28
Full text not available from this repository.Abstract
Ransomware attacks have emerged as a challenging threat in today's digital landscape, triggering worry among individuals or businesses and causing severe impairment to industries’ critical infrastructure. Detecting these unpredictable attacks in their early stages is paramount to mitigating their impact. This study presents an advanced comparative analysis of ransomware anomaly detection techniques enriched by the integration of hyperparameter optimization. By joining the interaction between pioneering anomaly detection algorithms and precision-tuned hyperparameters, we aim to increase the efficiency and accuracy of detecting ransomware incursions. This research uncovers their fundamental strengths and essential limitations by exploring diverse anomaly detection methodologies, including Medium Tree, Medium Gaussian SVM, Medium KNN, and Medium Neural Networks. Using state-of-the-art hyperparameter optimization techniques such as Grid Search, Random Search, and Bayesian Optimization, we comprehensively evaluate the impact of fine-tuned configurations on detection performance. Our experimental insights reveal that careful optimization of hyperparameters significantly enhances the ransomware detection capabilities of these algorithms. Precision, recall, and F1-score metrics consistently improve, securing the defense mechanisms against ransomware. By encapsulating these findings within the broader context of cybersecurity and anomaly detection, this study contributes to the refinement of ransomware detection methodologies. It offers a strategic route for future research in this critical threat domain.
| Item Type: | Book Chapter |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | School of Information Technology, Engineering, Mathematics and Physics (STEMP) |
| Depositing User: | Priynka Sharma |
| Date Deposited: | 08 May 2025 03:21 |
| Last Modified: | 08 May 2025 03:21 |
| URI: | https://repository.usp.ac.fj/id/eprint/14897 |
Actions (login required)
 |
View Item |