Summary of Ransomware Detection Using Stacked Autoencoder For Feature Selection, by Mike Nkongolo and Mahmut Tokmak
Ransomware detection using stacked autoencoder for feature selection
by Mike Nkongolo, Mahmut Tokmak
First submitted to arxiv on: 17 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed advanced ransomware detection and classification method combines a Stacked Autoencoder (SAE) for precise feature selection with a Long Short Term Memory (LSTM) classifier to enhance ransomware stratification accuracy. The SAE is trained on the UGRansome dataset, and its learned weights and activations are analyzed to identify essential features for distinguishing ransomware families from other malware. The study optimizes the model’s performance through extensive experiments using up to 400 epochs and varying learning rates. The results demonstrate the outstanding performance of the SAE-LSTM model across all ransomware families, with high precision, recall, and F1 score values. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers created a new way to detect and classify different types of malware. They used a combination of two machine learning models: a Stacked Autoencoder (SAE) to select the most important features and a Long Short Term Memory (LSTM) classifier to make predictions. The SAE was trained on a dataset called UGRansome, which contains information about different types of malware. By looking at how the SAE learned, they found the best features to use for classification. They then tested their model using many different combinations of parameters and found that it works very well, with an accuracy rate of 99%. |
Keywords
* Artificial intelligence * Autoencoder * Classification * F1 score * Feature selection * Lstm * Machine learning * Precision * Recall
