Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386322011> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4386322011 endingPage "1" @default.
- W4386322011 startingPage "1" @default.
- W4386322011 abstract "The purpose of malicious traffic detection and identification in the Internet of Things is to detect the intrusion of malicious traffic within the Internet of Things network into Internet of Things devices. Detection and identification play a key role in ensuring the security of the Internet of Things. At this time, great success has been achieved with deep learning in the field of malicious traffic detection and identification. However, due to resource limitations such as computation weaknesses and low edge network node storage capacity in the Internet of Things, a high-complexity model based on deep learning cannot be deployed and applied. In this paper, we propose a lightweight malicious traffic detection and recognition model named Lightweight Knowledge Distillation-Space Time Neural Network (LKD-STNN) based on knowledge distillation deep learning for the Internet of Things. We use knowledge distillation to build a lightweight student model by depth-wise separable convolution and BiLSTM to realize a lightweight student model and obtain multidimensional characteristic information. According to the characteristics of knowledge distillation, we propose an adaptive temperature function that can adaptively and dynamically change the temperature during the process of knowledge transfer so that different softening characteristics can be obtained during the training process. Then, the weight is updated by combining loss functions to improve the performance of the student model. The experimental results show that with the publicly available malicious traffic datasets for the Internet of Things, the ToN-IoT and IoT-23, our model not only reduces the complexity of the model and the number of model parameters to less than 1% of the teacher model but also reaches an accuracy of more than 98%, indicating that our model can be applied to the multiclassification identification of malicious traffic in the Internet of Things." @default.
- W4386322011 created "2023-09-01" @default.
- W4386322011 creator A5001671734 @default.
- W4386322011 creator A5047252231 @default.
- W4386322011 creator A5050240108 @default.
- W4386322011 creator A5087159582 @default.
- W4386322011 date "2023-01-01" @default.
- W4386322011 modified "2023-09-26" @default.
- W4386322011 title "LKD-STNN: A Lightweight Malicious Traffic Detection Method for Internet of Things Based on Knowledge Distillation" @default.
- W4386322011 doi "https://doi.org/10.1109/jiot.2023.3310794" @default.
- W4386322011 hasPublicationYear "2023" @default.
- W4386322011 type Work @default.
- W4386322011 citedByCount "0" @default.
- W4386322011 crossrefType "journal-article" @default.
- W4386322011 hasAuthorship W4386322011A5001671734 @default.
- W4386322011 hasAuthorship W4386322011A5047252231 @default.
- W4386322011 hasAuthorship W4386322011A5050240108 @default.
- W4386322011 hasAuthorship W4386322011A5087159582 @default.
- W4386322011 hasConcept C110875604 @default.
- W4386322011 hasConcept C111919701 @default.
- W4386322011 hasConcept C116834253 @default.
- W4386322011 hasConcept C119857082 @default.
- W4386322011 hasConcept C136764020 @default.
- W4386322011 hasConcept C154945302 @default.
- W4386322011 hasConcept C26517878 @default.
- W4386322011 hasConcept C38652104 @default.
- W4386322011 hasConcept C41008148 @default.
- W4386322011 hasConcept C59822182 @default.
- W4386322011 hasConcept C86803240 @default.
- W4386322011 hasConcept C98045186 @default.
- W4386322011 hasConceptScore W4386322011C110875604 @default.
- W4386322011 hasConceptScore W4386322011C111919701 @default.
- W4386322011 hasConceptScore W4386322011C116834253 @default.
- W4386322011 hasConceptScore W4386322011C119857082 @default.
- W4386322011 hasConceptScore W4386322011C136764020 @default.
- W4386322011 hasConceptScore W4386322011C154945302 @default.
- W4386322011 hasConceptScore W4386322011C26517878 @default.
- W4386322011 hasConceptScore W4386322011C38652104 @default.
- W4386322011 hasConceptScore W4386322011C41008148 @default.
- W4386322011 hasConceptScore W4386322011C59822182 @default.
- W4386322011 hasConceptScore W4386322011C86803240 @default.
- W4386322011 hasConceptScore W4386322011C98045186 @default.
- W4386322011 hasFunder F4320321001 @default.
- W4386322011 hasLocation W43863220111 @default.
- W4386322011 hasOpenAccess W4386322011 @default.
- W4386322011 hasPrimaryLocation W43863220111 @default.
- W4386322011 hasRelatedWork W2329452785 @default.
- W4386322011 hasRelatedWork W2356380379 @default.
- W4386322011 hasRelatedWork W2961085424 @default.
- W4386322011 hasRelatedWork W3046775127 @default.
- W4386322011 hasRelatedWork W3170094116 @default.
- W4386322011 hasRelatedWork W4285260836 @default.
- W4386322011 hasRelatedWork W4286629047 @default.
- W4386322011 hasRelatedWork W4306321456 @default.
- W4386322011 hasRelatedWork W4306674287 @default.
- W4386322011 hasRelatedWork W4224009465 @default.
- W4386322011 isParatext "false" @default.
- W4386322011 isRetracted "false" @default.
- W4386322011 workType "article" @default.