Trust in Intrusion Detection Systems: An Investigation of Performance Analysis for Machine Learning and Deep Learning Models
To design and develop AI-based cybersecurity systems (e.g., intrusion detection system (IDS)), users can justifiably trust, one needs to evaluate the impact of trust using machine learning and deep learning technologies. To guide the design and implementation of trusted AI-based systems in IDS, this...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/5538896 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832566499061006336 |
|---|---|
| author | Basim Mahbooba Radhya Sahal Wael Alosaimi Martin Serrano |
| author_facet | Basim Mahbooba Radhya Sahal Wael Alosaimi Martin Serrano |
| author_sort | Basim Mahbooba |
| collection | DOAJ |
| description | To design and develop AI-based cybersecurity systems (e.g., intrusion detection system (IDS)), users can justifiably trust, one needs to evaluate the impact of trust using machine learning and deep learning technologies. To guide the design and implementation of trusted AI-based systems in IDS, this paper provides a comparison among machine learning and deep learning models to investigate the trust impact based on the accuracy of the trusted AI-based systems regarding the malicious data in IDs. The four machine learning techniques are decision tree (DT), K nearest neighbour (KNN), random forest (RF), and naïve Bayes (NB). The four deep learning techniques are LSTM (one and two layers) and GRU (one and two layers). Two datasets are used to classify the IDS attack type, including wireless sensor network detection system (WSN-DS) and KDD Cup network intrusion dataset. A detailed comparison of the eight techniques’ performance using all features and selected features is made by measuring the accuracy, precision, recall, and F1-score. Considering the findings related to the data, methodology, and expert accountability, interpretability for AI-based solutions also becomes demanded to enhance trust in the IDS. |
| format | Article |
| id | doaj-art-b2497f8035ad4a6f875d2bc8dda8d24d |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-b2497f8035ad4a6f875d2bc8dda8d24d2025-02-03T01:04:04ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/55388965538896Trust in Intrusion Detection Systems: An Investigation of Performance Analysis for Machine Learning and Deep Learning ModelsBasim Mahbooba0Radhya Sahal1Wael Alosaimi2Martin Serrano3Data Science Institute Insight Centre for Data Analytics, National University of Ireland Galway, Galway, IrelandFaculty of Computer Science and Engineering, Hodeidah University, Al Hudaydah, YemenDepartment of Information Technology, College of Computers and Information Technology, Taif University, P.O.Box 11099, Taif 21944, Saudi ArabiaData Science Institute Insight Centre for Data Analytics, National University of Ireland Galway, Galway, IrelandTo design and develop AI-based cybersecurity systems (e.g., intrusion detection system (IDS)), users can justifiably trust, one needs to evaluate the impact of trust using machine learning and deep learning technologies. To guide the design and implementation of trusted AI-based systems in IDS, this paper provides a comparison among machine learning and deep learning models to investigate the trust impact based on the accuracy of the trusted AI-based systems regarding the malicious data in IDs. The four machine learning techniques are decision tree (DT), K nearest neighbour (KNN), random forest (RF), and naïve Bayes (NB). The four deep learning techniques are LSTM (one and two layers) and GRU (one and two layers). Two datasets are used to classify the IDS attack type, including wireless sensor network detection system (WSN-DS) and KDD Cup network intrusion dataset. A detailed comparison of the eight techniques’ performance using all features and selected features is made by measuring the accuracy, precision, recall, and F1-score. Considering the findings related to the data, methodology, and expert accountability, interpretability for AI-based solutions also becomes demanded to enhance trust in the IDS.http://dx.doi.org/10.1155/2021/5538896 |
| spellingShingle | Basim Mahbooba Radhya Sahal Wael Alosaimi Martin Serrano Trust in Intrusion Detection Systems: An Investigation of Performance Analysis for Machine Learning and Deep Learning Models Complexity |
| title | Trust in Intrusion Detection Systems: An Investigation of Performance Analysis for Machine Learning and Deep Learning Models |
| title_full | Trust in Intrusion Detection Systems: An Investigation of Performance Analysis for Machine Learning and Deep Learning Models |
| title_fullStr | Trust in Intrusion Detection Systems: An Investigation of Performance Analysis for Machine Learning and Deep Learning Models |
| title_full_unstemmed | Trust in Intrusion Detection Systems: An Investigation of Performance Analysis for Machine Learning and Deep Learning Models |
| title_short | Trust in Intrusion Detection Systems: An Investigation of Performance Analysis for Machine Learning and Deep Learning Models |
| title_sort | trust in intrusion detection systems an investigation of performance analysis for machine learning and deep learning models |
| url | http://dx.doi.org/10.1155/2021/5538896 |
| work_keys_str_mv | AT basimmahbooba trustinintrusiondetectionsystemsaninvestigationofperformanceanalysisformachinelearninganddeeplearningmodels AT radhyasahal trustinintrusiondetectionsystemsaninvestigationofperformanceanalysisformachinelearninganddeeplearningmodels AT waelalosaimi trustinintrusiondetectionsystemsaninvestigationofperformanceanalysisformachinelearninganddeeplearningmodels AT martinserrano trustinintrusiondetectionsystemsaninvestigationofperformanceanalysisformachinelearninganddeeplearningmodels |