查詢結果分析
相關文獻
- 網站入侵偵測系統之分析與研究
- 自組織映射圖網路簡介
- 模糊類神經網路應用於集水區出流量之預測
- 類神經網路方法分析流量率定曲線之研究
- 應用於檔案傳輸協定的類神經網路入侵偵測系統
- NIDS防禦力探析工具開發與測試案例
- 應用類神經網路於股票技術指標聚類與預測分析之研究
- 類神經網路流量系集預報模式之應用
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
頁籤選單縮合
題 名 | 網站入侵偵測系統之分析與研究=Analysis and Study of Web Intrusion Detection System |
---|---|
作 者 | 施東河; 黃于爵; | 書刊名 | 資訊管理學報 |
卷 期 | 9:2 2003.01[民92.01] |
頁 次 | 頁183-214 |
分類號 | 312 |
關鍵詞 | 入侵偵測系統; 駭客; 類神經網路; 自組織映射圖網路; Intrusion detection system; Hacker; Neural network; Self-organizing map; SOM; |
語 文 | 中文(Chinese) |
中文摘要 | 網路安全對MIS資訊人員來說非常重要,然而技術人員的技術與知識越來越難跟上不斷出現的安全漏洞與攻擊手法。在日新月異的資訊安全問題中,如何及時找出網路安全的弱點,適時地、有效率的定期評估稽核自我網路安全狀況,成了當前企業與MIS資訊人員首要關切的議題。本文除廣泛搜集現有市面上所有的網站入侵行為與攻擊軟體外,並根據國內外入侵偵測系統的探討,提出綜合Network-based misuse model與Host-based anomaly model的WIDS入侵偵測系統。本研究採用額神經網路中的自組織映射圖網路架構,並試圖提出一套具有學習能力的WIDS網站入侵偵測系統,期望能解決日新月異不斷翻新的攻擊手法,使得系統得以自我學習保護,使駭客攻擊傷害能降到最小。經過實證,本研究之入侵偵測系統正確率高達86%以上。 |
英文摘要 | Network security to MIS personnel is very important. However, the technique and knowledge of the technician is getting hard to catch up with more and more secure leak and attack skill. During the improving of information security, to find out the weakness of network security instantly is very important. Also, to efficiently and correctly estimate and examine one’s own security condition has become the first important theme for current enterprise and MIS personnel. Our research, adopt the neural network type of SOM (Self-Organizing Map) structure, and try to propose a self-learning WIDS (Web Intrusion Detection System) which have the learning ability to detect the invade of network system. Our expectation is to solve the continuously changed invading attack problems. Through our WIDS (Web Intrusion Detection System), provided our system self-study ability so learn to protect system itself, also minimize hackers’ attack. After testing and verifying, our research of WIDS (Web Intrusion Detection System) can be successfully detected up to 86% correctness. |
本系統中英文摘要資訊取自各篇刊載內容。