A Framework for Predicting Network Security Situation Based on the Improved LSTM
In recent years, raw security situation data cannot be utilized well by fully connected neural networks. Generally, a cyberinfiltration is a gradual process and there are logical associations between future situation and historical information.Taking the factors into account, this paper proposes a f...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
European Alliance for Innovation (EAI)
2020-06-01
|
| Series: | EAI Endorsed Transactions on Collaborative Computing |
| Subjects: | |
| Online Access: | https://eudl.eu/pdf/10.4108/eai.12-6-2020.165278 |
| _version_ | 1819012329414590464 |
|---|---|
| author | Shixuan Li Dongmei Zhao Qingru Li |
| author_facet | Shixuan Li Dongmei Zhao Qingru Li |
| author_sort | Shixuan Li |
| collection | DOAJ |
| description | In recent years, raw security situation data cannot be utilized well by fully connected neural networks. Generally, a cyberinfiltration is a gradual process and there are logical associations between future situation and historical information.Taking the factors into account, this paper proposes a framework to predict network security situation. According theneeds of this framework, we improve Long Short-Term Memory (LSTM) with Cross-Entropy function, Rectified LinearUnit and appropriate layer stacking. Modules are designed in the framework to transform raw data into quantitative results.Finally, the performance is evaluated on KDD CUP 99 dataset and UNSW-NB15 dataset. Experiments prove that theframework built with the improved LSTM has better performance to predict network security situation in the near future.The framework achieves a relatively practical prediction of network security situation, helping provide advanced measuresto improve network security. |
| first_indexed | 2024-12-21T01:42:19Z |
| format | Article |
| id | doaj.art-7a56878154fe48fcb3d53a81b121c351 |
| institution | Directory Open Access Journal |
| issn | 2312-8623 |
| language | English |
| last_indexed | 2024-12-21T01:42:19Z |
| publishDate | 2020-06-01 |
| publisher | European Alliance for Innovation (EAI) |
| record_format | Article |
| series | EAI Endorsed Transactions on Collaborative Computing |
| spelling | doaj.art-7a56878154fe48fcb3d53a81b121c3512022-12-21T19:20:07ZengEuropean Alliance for Innovation (EAI)EAI Endorsed Transactions on Collaborative Computing2312-86232020-06-0141310.4108/eai.12-6-2020.165278A Framework for Predicting Network Security Situation Based on the Improved LSTMShixuan Li0Dongmei Zhao1Qingru Li2College of Computer and Cyber Security, Hebei Normal University, Shijiazhuang 050024, ChinaHebei Key Laboratory of Network & Information Security, Shijiazhuang 050024, ChinaCollege of Computer and Cyber Security, Hebei Normal University, Shijiazhuang 050024, ChinaHebei Key Laboratory of Network & Information Security, Shijiazhuang 050024, ChinaCollege of Computer and Cyber Security, Hebei Normal University, Shijiazhuang 050024, ChinaHebei Key Laboratory of Network & Information Security, Shijiazhuang 050024, ChinaIn recent years, raw security situation data cannot be utilized well by fully connected neural networks. Generally, a cyberinfiltration is a gradual process and there are logical associations between future situation and historical information.Taking the factors into account, this paper proposes a framework to predict network security situation. According theneeds of this framework, we improve Long Short-Term Memory (LSTM) with Cross-Entropy function, Rectified LinearUnit and appropriate layer stacking. Modules are designed in the framework to transform raw data into quantitative results.Finally, the performance is evaluated on KDD CUP 99 dataset and UNSW-NB15 dataset. Experiments prove that theframework built with the improved LSTM has better performance to predict network security situation in the near future.The framework achieves a relatively practical prediction of network security situation, helping provide advanced measuresto improve network security.https://eudl.eu/pdf/10.4108/eai.12-6-2020.165278network security situationdeep learningsituation predictionneural networklstm |
| spellingShingle | Shixuan Li Dongmei Zhao Qingru Li A Framework for Predicting Network Security Situation Based on the Improved LSTM EAI Endorsed Transactions on Collaborative Computing network security situation deep learning situation prediction neural network lstm |
| title | A Framework for Predicting Network Security Situation Based on the Improved LSTM |
| title_full | A Framework for Predicting Network Security Situation Based on the Improved LSTM |
| title_fullStr | A Framework for Predicting Network Security Situation Based on the Improved LSTM |
| title_full_unstemmed | A Framework for Predicting Network Security Situation Based on the Improved LSTM |
| title_short | A Framework for Predicting Network Security Situation Based on the Improved LSTM |
| title_sort | framework for predicting network security situation based on the improved lstm |
| topic | network security situation deep learning situation prediction neural network lstm |
| url | https://eudl.eu/pdf/10.4108/eai.12-6-2020.165278 |
| work_keys_str_mv | AT shixuanli aframeworkforpredictingnetworksecuritysituationbasedontheimprovedlstm AT dongmeizhao aframeworkforpredictingnetworksecuritysituationbasedontheimprovedlstm AT qingruli aframeworkforpredictingnetworksecuritysituationbasedontheimprovedlstm AT shixuanli frameworkforpredictingnetworksecuritysituationbasedontheimprovedlstm AT dongmeizhao frameworkforpredictingnetworksecuritysituationbasedontheimprovedlstm AT qingruli frameworkforpredictingnetworksecuritysituationbasedontheimprovedlstm |