Summary of Detection-rate-emphasized Multi-objective Evolutionary Feature Selection For Network Intrusion Detection, by Zi-hang Cheng et al.
Detection-Rate-Emphasized Multi-objective Evolutionary Feature Selection for Network Intrusion Detection
by Zi-Hang Cheng, Haopu Shang, Chao Qian
First submitted to arxiv on: 13 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed DR-MOFS method optimizes feature selection in network intrusion detection as a three-objective problem, considering number of features, classification accuracy, and detection rate simultaneously. This addresses the limitation of previous multi-objective evolutionary algorithms (MOEAs) that only considered two objectives, leading to unsatisfactory performance on detection rates. The proposed approach demonstrates improved results on NSL-KDD and UNSW-NB15 datasets, featuring reduced feature sets, higher accuracy, and enhanced detection rates. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Network intrusion detection is a crucial issue in cybersecurity. Machine learning techniques have been used to build detection systems, but feature selection is necessary due to the large number of features describing network connections. Some researchers use multi-objective evolutionary algorithms (MOEAs) for feature selection, focusing on the number of features and classification accuracy. However, this approach often misses real attacks, leading to huge losses. This paper proposes a new method, DR-MOFS, which optimizes feature selection as a three-objective problem considering number of features, accuracy, and detection rate simultaneously. The results show that this method can outperform previous approaches on popular datasets. |
Keywords
* Artificial intelligence * Classification * Feature selection * Machine learning
