PHÁT HIỆN XÂM NHẬP SỬ DỤNG TÍNH NĂNG LUỒNG MẠNG CHO MẠNG ĐƯỢC XÁC ĐỊNH BẰNG PHẦN MỀM

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Văn Dần Dương, Minh Thanh Tạ, Nam Khánh Trần

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Journal of Science and Technique: Section on Information and Communication Technology, 2023

Mô tả vật lý: tr.75

Bộ sưu tập: Báo, Tạp chí

ID: 372072

Thêm vào giỏ Liên kết toàn văn

In recent years, Software-Defined Networking (SDN) is a new network architecture that has been gaining popularity. This promises to simplify network control and management with centralized control of the network, but it also increases the risk of a single point of failure (SPOF) in the network. To mitigate SPOF, more cyber security research is needed on SDN networks. On the other hand, intrusion detection systems (IDSs) play a crucial role in SDN security by dealing with external threats. Machine learning-based IDSs are well-suited for SDN because they can be trained on a centralized controller. However, there is limited research on SDN intrusion detection systems. Existing literature often treats SDN intrusion detection as similar to intrusion detection in traditional computer systems. This approach can be problematic because SDN networks have different characteristics than traditional computer systems. In this paper, we propose a new method for SDN intrusion detection using machine learning. Our method addresses the problem of data imbalance, which is a common problem with machine learning datasets. We also evaluate our method on the most recent public SDN intrusion detection dataset. Our results show that our method can achieve high accuracy and low false alarm rates. Finally, we evaluate the performance of our method in two different SDN scenarios: with and without load balancing. Our results show that our method can achieve high performance in both scenarios.Trong những năm gần đây, Mạng được xác định bằng phần mềm (SDN) là một kiến trúc mạng mới đang trở nên phổ biến. Điều này hứa hẹn sẽ đơn giản hóa việc kiểm soát và quản lý mạng với khả năng kiểm soát mạng tập trung, nhưng nó cũng làm tăng nguy cơ xảy ra lỗi một điểm (SPOF) trong mạng. Để giảm thiểu SPOF, cần có thêm nghiên cứu về an ninh mạng trên mạng SDN. Mặt khác, hệ thống phát hiện xâm nhập (IDS) đóng một vai trò quan trọng trong bảo mật SDN bằng cách xử lý các mối đe dọa bên ngoài. IDS dựa trên máy học rất phù hợp với SDN vì chúng có thể được huấn luyện trên bộ điều khiển tập trung. Tuy nhiên, nghiên cứu về hệ thống phát hiện xâm nhập SDN còn hạn chế. Các tài liệu hiện có thường coi việc phát hiện xâm nhập SDN tương tự như phát hiện xâm nhập trong các hệ thống máy tính truyền thống. Cách tiếp cận này có thể có vấn đề vì mạng SDN có những đặc điểm khác với hệ thống máy tính truyền thống. Trong bài báo này, chúng tôi đề xuất một phương pháp mới để phát hiện xâm nhập SDN bằng cách sử dụng máy học. Phương pháp của chúng tôi giải quyết vấn đề mất cân bằng dữ liệu, đây là một vấn đề phổ biến với bộ dữ liệu học máy. Chúng tôi cũng đánh giá phương pháp của mình trên tập dữ liệu phát hiện xâm nhập SDN công khai gần đây nhất. Kết quả của chúng tôi cho thấy phương pháp này có thể đạt được độ chính xác cao và tỷ lệ cảnh báo sai thấp. Cuối cùng, chúng tôi đánh giá hiệu suất của phương pháp trong hai kịch bản SDN khác nhau: có và không có cân bằng tải. Kết quả này cho thấy phương pháp của chúng tôi có thể đạt được hiệu suất cao trong cả hai kịch bản.

1. Đọc trực tuyến

1. Đọc trực tuyến

Tạo bộ sưu tập với mã QR