Loading...

Deep Learning Based Enhancement of Intrusion Detection Methods

Soltani, Mahdi | 2024

10 Viewed
  1. Type of Document: Ph.D. Dissertation
  2. Language: Farsi
  3. Document No: 56918 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Jahangir, Amir Hossein; Jafari Siavoshani, Mahdi
  7. Abstract:
  8. We live in the cyber era in which network-based technologies have become omnipresent. Meanwhile, threats and attacks are rapidly growing in cyberspace. Nowadays, some signature-based intrusion detection systems try to detect these malicious traffics. However, as new vulnerabilities and new zero-day attacks appear, there is a growing risk of bypassing the current intrusion detection systems. Many research studies have worked on machine learning algorithms for intrusion detection applications. Their major weakness is to consider the different aspects of network security concurrently. For example, continuous concept drift in normal and abnormal traffic, the permanent appearance of zero-day attacks, and different traffic behavior in each organization are some of the aspects that make the main differences between the network security scope and other research domains. In this research proposal, we first use deep learning techniques to detect content-based attacks. Then an adaptive cooperative framework is proposed, which could adapt itself to the behaviors of network traffics without needing any labeled traffic
  9. Keywords:
  10. Intrusion Detection System ; Deep Learning ; Concept Drift ; Anomaly Detection ; Unsupervised Learning ; Cooperative Detection ; Content Based Attacks Detection

 Digital Object List

 Bookmark

...see more