Deep learning models for malware traffic detection and classification: a focus on pruning and hyperband for resource optimization

dc.contributor.advisorChavula, Josiah
dc.contributor.authorSheetekela, Sanette Penelao
dc.date.accessioned2026-07-23T09:08:16Z
dc.date.available2026-07-23T09:08:16Z
dc.date.issued2026
dc.date.updated2026-07-23T09:06:36Z
dc.description.abstractNetwork traffic encryption is increasingly being adopted as the norm for communication technologies because of its capacity to protect privacy. Conversely, concealing data from unintended recipients presents an additional issue in the communication system, as encrypted data makes it challenging to detect malware using traditional methods such as deep packet inspection. Deep learning (DL) has emerged as a powerful technique for detecting malware in encrypted traffic flows. However, their high processing needs make it hard to use them in places with limited resources, such as Internet of Things (IoT) and edge devices. This study investigated the effectiveness of post-training weight and neuron pruning on three DL models—Multilayer Perceptron (MLP), One-dimensional convolutional Neural Networks (1D-CNN), and Long Short-term Memory Networks (LSTM)—to optimize resource usage while maintaining detection accuracy. In addition, the study integrated Hyperband, a resource-efficient hyperparameter tuning method that dynamically allocates computational resources based on intermediate performance evaluations to enhance pruned models. The CTU-13 dataset was used to assess how pruning rates influence detection performance and resource efficiency, with an emphasis on the trade-offs introduced by weight pruning (WP) and neuron pruning (NP). Our findings revealed that moderate pruning of 20% to 40% maintained or improved model accuracy while decreasing the model size by up to 40%, inference time by 30%, and memory usage by 10%. Among the models, 1D-CNN consistently provided the optimal balance between performance and computational efficiency. Regarding pruning techniques, structured neuron pruning (NP) has proven to be the most effective method, achieving significant reductions in model size and memory usage without compromising on detection performance. In contrast, unstructured weight pruning (WP) primarily reduced the number of active weights in the model by setting them to zero, which helped lower memory usage during processing; however, no compression was applied to the actual file size. Overall, the findings showed that adaptive tuning, when combined with pruning, offers an effective approach for building high-performing lightweight models that can be implemented in resource-constrained environments for encrypted malware traffic flow classification.
dc.identifier.apacitationSheetekela, S. P. (2026). <i>Deep learning models for malware traffic detection and classification: a focus on pruning and hyperband for resource optimization</i>. (). University of Cape Town ,Faculty of Science ,Department of Computer Science. Retrieved from http://hdl.handle.net/11427/43661en_ZA
dc.identifier.chicagocitationSheetekela, Sanette Penelao. <i>"Deep learning models for malware traffic detection and classification: a focus on pruning and hyperband for resource optimization."</i> ., University of Cape Town ,Faculty of Science ,Department of Computer Science, 2026. http://hdl.handle.net/11427/43661en_ZA
dc.identifier.citationSheetekela, S.P. 2026. Deep learning models for malware traffic detection and classification: a focus on pruning and hyperband for resource optimization. . University of Cape Town ,Faculty of Science ,Department of Computer Science. http://hdl.handle.net/11427/43661en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Sheetekela, Sanette Penelao AB - Network traffic encryption is increasingly being adopted as the norm for communication technologies because of its capacity to protect privacy. Conversely, concealing data from unintended recipients presents an additional issue in the communication system, as encrypted data makes it challenging to detect malware using traditional methods such as deep packet inspection. Deep learning (DL) has emerged as a powerful technique for detecting malware in encrypted traffic flows. However, their high processing needs make it hard to use them in places with limited resources, such as Internet of Things (IoT) and edge devices. This study investigated the effectiveness of post-training weight and neuron pruning on three DL models—Multilayer Perceptron (MLP), One-dimensional convolutional Neural Networks (1D-CNN), and Long Short-term Memory Networks (LSTM)—to optimize resource usage while maintaining detection accuracy. In addition, the study integrated Hyperband, a resource-efficient hyperparameter tuning method that dynamically allocates computational resources based on intermediate performance evaluations to enhance pruned models. The CTU-13 dataset was used to assess how pruning rates influence detection performance and resource efficiency, with an emphasis on the trade-offs introduced by weight pruning (WP) and neuron pruning (NP). Our findings revealed that moderate pruning of 20% to 40% maintained or improved model accuracy while decreasing the model size by up to 40%, inference time by 30%, and memory usage by 10%. Among the models, 1D-CNN consistently provided the optimal balance between performance and computational efficiency. Regarding pruning techniques, structured neuron pruning (NP) has proven to be the most effective method, achieving significant reductions in model size and memory usage without compromising on detection performance. In contrast, unstructured weight pruning (WP) primarily reduced the number of active weights in the model by setting them to zero, which helped lower memory usage during processing; however, no compression was applied to the actual file size. Overall, the findings showed that adaptive tuning, when combined with pruning, offers an effective approach for building high-performing lightweight models that can be implemented in resource-constrained environments for encrypted malware traffic flow classification. DA - 2026 DB - OpenUCT DP - University of Cape Town KW - Encrypted Traffic Flows KW - Deep Learning KW - Malware Detection KW - Post-training Pruning KW - Weight Pruning KW - Neuron Pruning KW - Hyperband Optimization KW - Binary Classification KW - Multiclass Classification KW - Resource-constrained Environments LK - https://open.uct.ac.za PB - University of Cape Town PY - 2026 T1 - Deep learning models for malware traffic detection and classification: a focus on pruning and hyperband for resource optimization TI - Deep learning models for malware traffic detection and classification: a focus on pruning and hyperband for resource optimization UR - http://hdl.handle.net/11427/43661 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/43661
dc.identifier.vancouvercitationSheetekela SP. Deep learning models for malware traffic detection and classification: a focus on pruning and hyperband for resource optimization. []. University of Cape Town ,Faculty of Science ,Department of Computer Science, 2026 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/43661en_ZA
dc.language.isoen
dc.language.rfc3066eng
dc.publisher.departmentDepartment of Computer Science
dc.publisher.facultyFaculty of Science
dc.publisher.institutionUniversity of Cape Town
dc.subjectEncrypted Traffic Flows
dc.subjectDeep Learning
dc.subjectMalware Detection
dc.subjectPost-training Pruning
dc.subjectWeight Pruning
dc.subjectNeuron Pruning
dc.subjectHyperband Optimization
dc.subjectBinary Classification
dc.subjectMulticlass Classification
dc.subjectResource-constrained Environments
dc.titleDeep learning models for malware traffic detection and classification: a focus on pruning and hyperband for resource optimization
dc.typeThesis / Dissertation
dc.type.qualificationlevelMasters
dc.type.qualificationlevelMSc
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_sci_2026_sheetekela sanette penelao.pdf
Size:
11.25 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections