Publication Date
Fall 2023
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Fabio Di Troia
Second Advisor
Thomas Austin
Third Advisor
Venkat J Thodima
Keywords
Malware detection, Machine learning algorithms, Convolutional Neural Networks, AlexNet, LeNet, VGGNet
Abstract
In recent years, deep learning has emerged as a powerful tool for image classification tasks. However, the performance of individual deep learning models can be limited by their architecture and training data. In this project, various Convolutional Neural Network (CNN) architectures are proposed to train the malware data for feature extraction for various color coordinates such as L, CMYK, RGB, RGBA, and YCbCr. Different optimization techniques like Stochastic Gradient Descent, Root Mean Square Propagation, Ada Delta, Adam, and Adaptive Gradient are used to minimize errors in the trained data, leading to enhanced accuracy. The proposed ensemble deep learning model for image classification, combining strengths from popular CNN architectures like LeNet, AlexNet, VGG, ResNet, and GoogleNet, is utilized for feature extraction. This model employs a weighted average of predictions from each model to make the final classification decision. The performance of the proposed model is evaluated using several benchmark datasets, and the experimental results demonstrate that the ensemble model achieves higher accuracy and robustness compared to individual models and other state-of-the-art ensemble methods. Ablation studies were conducted to analyze the contribution of each model to the ensemble performance. The results reveal that each model contributes differently, and the combination of all models achieves the best performance. The proposed ensemble deep learning model, incorporating AlexNet, LeNet, VGG, ResNet, and GoogleNet architectures, attains state-of-the-art performance across several benchmark datasets. This versatile model can be applied to various image classification tasks, including object recognition, scene understanding, and medical image analysis.
Recommended Citation
Pamanji, Rishika, "Advances in Robustness of Image-based Malware Detection" (2023). Master's Projects. 1317.
https://scholarworks.sjsu.edu/etd_projects/1317
