Multi-Modal Features Representation-Based Convolutional Neural Network Model for Malicious Website Detection
Web applications have proliferated across various business sectors, serving as essential tools for billions of users in their daily lives activities. However, many of these applications are malicious which is a major threat to Internet users as they can steal sensitive information, install malware,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10375501/ |
| _version_ | 1827378247317323776 |
|---|---|
| author | Mohammed Alsaedi Fuad A. Ghaleb Faisal Saeed Jawad Ahmad Mohammed Alasli |
| author_facet | Mohammed Alsaedi Fuad A. Ghaleb Faisal Saeed Jawad Ahmad Mohammed Alasli |
| author_sort | Mohammed Alsaedi |
| collection | DOAJ |
| description | Web applications have proliferated across various business sectors, serving as essential tools for billions of users in their daily lives activities. However, many of these applications are malicious which is a major threat to Internet users as they can steal sensitive information, install malware, and propagate spam. Detecting malicious websites by analyzing web content is ineffective due to the complexity of extraction of the representative features, the huge data volume, the evolving nature of the malicious patterns, the stealthy nature of the attacks, and the limitations of traditional classifiers. Uniform Resource Locators (URL) features are static and can often provide immediate insights about the website without the need to load its content. However, existing solutions for detecting malicious web applications through web content analysis often struggle due to complex feature extraction, massive data volumes, evolving attack patterns, and limitations of traditional classifiers. Leveraging solely lexical URL features proves insufficient, potentially leading to inaccurate classifications. This study proposes a multimodal representation approach that fuses textual and image-based features to enhance the performance of the malicious website detection. Textual features facilitate the deep learning model’s ability to understand and represent detailed semantic information related to attack patterns, while image features are effective in recognizing more general malicious patterns. In doing so, patterns that are hidden in textual format may be recognizable in image format. Two Convolutional Neural Network (CNN) models were constructed to extract the hidden features from both textual and image-represented features. The output layers of both models were combined and used as input for an artificial neural network classifier for decision-making. Results show the effectiveness of the proposed model when compared to other models. The overall performance in terms of Matthews Correlation Coefficient (MCC) was improved by 4.3% while the false positive rate was reduced by 1.5%. |
| first_indexed | 2024-03-08T12:53:14Z |
| format | Article |
| id | doaj.art-460a8a99a6f3459f8777952f5659381e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T12:53:14Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-460a8a99a6f3459f8777952f5659381e2024-01-20T00:00:49ZengIEEEIEEE Access2169-35362024-01-01127271728410.1109/ACCESS.2023.334807110375501Multi-Modal Features Representation-Based Convolutional Neural Network Model for Malicious Website DetectionMohammed Alsaedi0Fuad A. Ghaleb1https://orcid.org/0000-0002-1468-0655Faisal Saeed2https://orcid.org/0000-0002-2822-1708Jawad Ahmad3https://orcid.org/0000-0001-6289-8248Mohammed Alasli4https://orcid.org/0000-0002-3358-7050College of Computer Science and Engineering, Taibah University, Medina, Western Region, Saudi ArabiaFaculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Johor, MalaysiaDAAI Research Group, College of Computing and Digital Technology, Birmingham City University, Birmingham, U.KSchool of Computing, Engineering and the Built Environment, Edinburgh Napier University, Edinburgh, U.KCollege of Computer Science and Engineering, Taibah University, Medina, Western Region, Saudi ArabiaWeb applications have proliferated across various business sectors, serving as essential tools for billions of users in their daily lives activities. However, many of these applications are malicious which is a major threat to Internet users as they can steal sensitive information, install malware, and propagate spam. Detecting malicious websites by analyzing web content is ineffective due to the complexity of extraction of the representative features, the huge data volume, the evolving nature of the malicious patterns, the stealthy nature of the attacks, and the limitations of traditional classifiers. Uniform Resource Locators (URL) features are static and can often provide immediate insights about the website without the need to load its content. However, existing solutions for detecting malicious web applications through web content analysis often struggle due to complex feature extraction, massive data volumes, evolving attack patterns, and limitations of traditional classifiers. Leveraging solely lexical URL features proves insufficient, potentially leading to inaccurate classifications. This study proposes a multimodal representation approach that fuses textual and image-based features to enhance the performance of the malicious website detection. Textual features facilitate the deep learning model’s ability to understand and represent detailed semantic information related to attack patterns, while image features are effective in recognizing more general malicious patterns. In doing so, patterns that are hidden in textual format may be recognizable in image format. Two Convolutional Neural Network (CNN) models were constructed to extract the hidden features from both textual and image-represented features. The output layers of both models were combined and used as input for an artificial neural network classifier for decision-making. Results show the effectiveness of the proposed model when compared to other models. The overall performance in terms of Matthews Correlation Coefficient (MCC) was improved by 4.3% while the false positive rate was reduced by 1.5%.https://ieeexplore.ieee.org/document/10375501/Convolutional neural networkmalicious URL detectionmalicious website detectionmulti-modal features representationURL image representation |
| spellingShingle | Mohammed Alsaedi Fuad A. Ghaleb Faisal Saeed Jawad Ahmad Mohammed Alasli Multi-Modal Features Representation-Based Convolutional Neural Network Model for Malicious Website Detection IEEE Access Convolutional neural network malicious URL detection malicious website detection multi-modal features representation URL image representation |
| title | Multi-Modal Features Representation-Based Convolutional Neural Network Model for Malicious Website Detection |
| title_full | Multi-Modal Features Representation-Based Convolutional Neural Network Model for Malicious Website Detection |
| title_fullStr | Multi-Modal Features Representation-Based Convolutional Neural Network Model for Malicious Website Detection |
| title_full_unstemmed | Multi-Modal Features Representation-Based Convolutional Neural Network Model for Malicious Website Detection |
| title_short | Multi-Modal Features Representation-Based Convolutional Neural Network Model for Malicious Website Detection |
| title_sort | multi modal features representation based convolutional neural network model for malicious website detection |
| topic | Convolutional neural network malicious URL detection malicious website detection multi-modal features representation URL image representation |
| url | https://ieeexplore.ieee.org/document/10375501/ |
| work_keys_str_mv | AT mohammedalsaedi multimodalfeaturesrepresentationbasedconvolutionalneuralnetworkmodelformaliciouswebsitedetection AT fuadaghaleb multimodalfeaturesrepresentationbasedconvolutionalneuralnetworkmodelformaliciouswebsitedetection AT faisalsaeed multimodalfeaturesrepresentationbasedconvolutionalneuralnetworkmodelformaliciouswebsitedetection AT jawadahmad multimodalfeaturesrepresentationbasedconvolutionalneuralnetworkmodelformaliciouswebsitedetection AT mohammedalasli multimodalfeaturesrepresentationbasedconvolutionalneuralnetworkmodelformaliciouswebsitedetection |