Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.20803 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913812762853376 |
|---|---|
| author | Ajayi, Bamidele Barakat, Basel McGarry, Ken |
| author_facet | Ajayi, Bamidele Barakat, Basel McGarry, Ken |
| contents | This paper assesses the performance of five machine learning classifiers: Decision Tree, Naive Bayes, LightGBM, Logistic Regression, and Random Forest using latent representations learned by a Variational Autoencoder from malware datasets. Results from the experiments conducted on different training-test splits with different random seeds reveal that all the models perform well in detecting malware with ensemble methods (LightGBM and Random Forest) performing slightly better than the rest. In addition, the use of latent features reduces the computational cost of the model and the need for extensive hyperparameter tuning for improved efficiency of the model for deployment. Statistical tests show that these improvements are significant, and thus, the practical relevance of integrating latent space representation with traditional classifiers for effective malware detection in cybersecurity is established. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20803 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging VAE-Derived Latent Spaces for Enhanced Malware Detection with Machine Learning Classifiers Ajayi, Bamidele Barakat, Basel McGarry, Ken Cryptography and Security Machine Learning This paper assesses the performance of five machine learning classifiers: Decision Tree, Naive Bayes, LightGBM, Logistic Regression, and Random Forest using latent representations learned by a Variational Autoencoder from malware datasets. Results from the experiments conducted on different training-test splits with different random seeds reveal that all the models perform well in detecting malware with ensemble methods (LightGBM and Random Forest) performing slightly better than the rest. In addition, the use of latent features reduces the computational cost of the model and the need for extensive hyperparameter tuning for improved efficiency of the model for deployment. Statistical tests show that these improvements are significant, and thus, the practical relevance of integrating latent space representation with traditional classifiers for effective malware detection in cybersecurity is established. |
| title | Leveraging VAE-Derived Latent Spaces for Enhanced Malware Detection with Machine Learning Classifiers |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2503.20803 |