Abstract
Intrusion Detection Systems (IDS) play a vital role in safeguarding network security by monitoring and identifying both normal and intrusive activities. However, constructing an effective IDS from extensive datasets poses a significant challenge. The process of feature selection from these datasets is crucial, as it not only enhances accuracy but also reduces the time required to build the model. In this paper, we employ a modified version of the Student Psychology-Based Optimization (SPBO) algorithm to identify the most relevant features set for IDS. Following feature selection, various machine learning algorithms are employed for multi-level classification. To evaluate our approach, we utilize the NLS-KDD dataset. Our proposed algorithm surpasses several state-of-the-art feature selection methods in terms of accuracy, precision, recall, Fl-score, and finally faster convergence. Specif-ically, our proposed bio-inspired SPBO algorithm combined with the Random Forest (RF) algorithm achieves a comparable accuracy rate of 99.81 %. To ensure better comprehensibility, we employ two widely used Explainable Artificial Intelligence (XAI) techniques: SHapley Additive exPlanations (SHAP) and Local In-terpretable Model-Agnostic Explanations (LIME). These methods provide insightful explanations for our model's decisions, further enhancing its interpretability.
| Original language | English |
|---|---|
| Title of host publication | 2023 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE) |
| Publisher | IEEE |
| Pages | 1-6 |
| Number of pages | 6 |
| ISBN (Electronic) | 9798350341072 |
| ISBN (Print) | 9798350341089 |
| DOIs | |
| Publication status | Published - 2023 |
| Event | 10th Asia-Pacific Conference on Computer Science and Data Engineering: IEEE CSDE 2023 - Shangri-La Fijian Resort, Yanuca Island, Fiji Duration: 04 Dec 2023 → 06 Dec 2023 https://web.archive.org/web/20221220075303/https://ieee-csde.org/csde2023/ (Wayback Machine link to website) |
Conference
| Conference | 10th Asia-Pacific Conference on Computer Science and Data Engineering |
|---|---|
| Abbreviated title | Secure Data Via Blockchain |
| Country/Territory | Fiji |
| City | Yanuca Island |
| Period | 04/12/23 → 06/12/23 |
| Other | The 10th IEEE CSDE 2023, the Asia-Pacific Conference on Computer Science and Data Engineering 2023, offers an ideal opportunity for researchers, engineers, academics and students from all over the world to bring the latest technological advances and applications in popular computer science and data engineering areas, as well as to network and promote the discipline. Cutting-edge researchers will present keynote speeches during a three-day program featuring tutorials and technical sessions on theory, analysis, design, testing and advances in computer science, data science and data engineering. Scholarships are offered for students to cover the cost of attending the conference and reduced registration fees apply to delegates from UN least developed countries. The papers presented at the conference will be included in the IEEE Digital Library. This year IEEE CSDE 2023 is being held at the Shangir-La’s Fijian Resort, Yanuca Island, Nadi, Fiji. Yanuca Island is a leading tourism, business and events city boasting arguably one of the best lifestyles in the world. The island is only 43.13 km far from the Nadi International Airport. Inspiration is on the horizon, and nature is at your doorstep on the private Yanuca Island, Shangri-La Fijian Resort, Yanuca Island, Fiji, offers the essence of an exclusive island hideaway yet is conveniently connected to the mainland by a causeway. The 443 ocean-view guest rooms take their inspiration from a traditional Fijian village featuring rich local culture and nature elements. The Conference is hosted and sponsored by the Computer Society, The University of the South Pacific, Fiji; The University of Fiji, Fiji, CQUniversity, Australia; Massy University, New Zealand and NPS Australia. |
| Internet address |
|