Deep Learning and Regularization Algorithms for Malicious Code Classification

Abstract

Network security has become a growing concern within the popularity and development of the Internet. Malicious code is one of the main threats in network security. Different types of malicious code have different functions and cause different harms. Therefore, improving the detection efficiency and recognition accuracy of malicious code is becoming an urgent problem to be solved. While traditional machine learning methods for malicious codes detection largely depend on hand-designed features with experts' knowledge of the domain, or focus on the images which comes from malicious code binary files. These methods spend too much time on feature extraction. With the emergence of a large amount of malicious code data, efficiency of traditional machine learning algorithms is getting worse and worse. In this paper, a workflow based on deep learning is proposed to detect and classify malicious codes. This workflow adopts convolutional neural network (CNN) and the regularization algorithms to classify malicious code with N_gram semantic feature as input of the model. The convolutional neural network can automatically extract the features of malicious code, while avoiding the need for manual feature selection. Regularization algorithms not only speed up the training process of the deep model, but also improve the generalization ability in the case of effective prevention of over-fitting of the model. The proposed method is compared with the state-of-the art methods and other deep learning models. Experimental results show that our workflow is able to improve the accuracy and efficiency of malicious code classification.

Hybridized Least Absolute Shrinkage Selection Operator and Cross-Validation Algorithm for Classification of Malware

“…𝑇𝑃 𝑇𝑃+𝐹𝑁 (14) Recall: It is defined as the total number of actual positive labels identified by the model. F-1 score: It is evaluated by measuring the harmonic mean of precision and recall, it is evaluated using the Eq.…”

“…Research using machine learning techniques in the detection of malware is increasing rapidly. Machine learning techniques are utilized in the analysis and selection of features to provide better classification performance [13][14][15]. To overcome the mentioned problems, the deep learning approach is utilized in this research.…”

Improved Marine Predators Algorithm Optimized BiGRU for Strip Exit Thickness Prediction

“…The strip exit thickness prediction methods based on deep learning models could automatically and effectively extract rich features, deeply mine the inherent laws of the data, and solve complex pattern recognition problems [9], [10], [11]. LSTM and GRU address the issues of gradient explosion and vanishing in RNNs [12], [13], demonstrating strong capabilities in learning nonlinear feature sequences, making them well-suited for handling sequential data.…”