Research Article
Malware Detection on Byte Streams of PDF Files Using Convolutional Neural Networks
Table 2
Description of comparative classifiers and parameter settings.
| Model | Description |
| Naïve bayes (NB) | (i) Probabilistic classifier based on the bayes’ theorem | (ii) Assumes the independence between features |
| Decision tree (DT) | (i) C4.5 classifier using J48 algorithm | (ii) Confidence factor for pruning: 0.25 |
| Support vector machine (SVM) | (i) Non-probabilistic binary classification model that finds a decision boundary with a maximum distance between two classes | (ii) Kernel: Poly | (iii) Exponent=1.0, Complexity c=1.0 | (iv) Trained via sequential minimal optimization algorithm [11] |
| Random forest (RF) | (i) Kind of ensemble model that generates final result by incorporating results of multiple decision-trees | (ii) #trees=100 | (iii) #features=log(#trees)+1 | (iv) Each tree has no depth-limitation |
|
|