Sign in Subscribe
Genetic research

Hybrid Approach for Intrusion Detection System Yields Improved Accuracy and Reduced Training Time

Strategic Insights

— 1 min read

A new study on engineering has reported a significant breakthrough in intrusion detection systems (IDS) through a hybrid approach that integrates slime mold algorithm (SMA) and genetic algorithm (GA) within a feature selection (FS) framework. The innovative approach, known as OSMOGA, is designed to enhance search efficiency and improve detection accuracy. According to the research, OSMOGA achieves superior classification accuracy on four different data sets, including NSL-KDD, KDD Cup'99, CICIDS2017, and UNSW-NB15.

Key Takeaways:

  • The study proposes a hybrid approach, OSMOGA, that integrates SMA and GA to improve IDS performance.
  • OSMOGA enhances search efficiency through opposition-based learning (OBL) and accelerates convergence.
  • The approach achieves superior detection accuracy, with classification accuracy rates of 98.64%, 98.99%, 99.43%, and 99.78% for the respective data sets.
  • The study demonstrates that OSMOGA significantly reduces training time through effective feature selection.
  • The OSMOGA approach is applied for FS in ID problems and is rigorously evaluated against well-established metaheuristic algorithms.
  • The research shows that OSMOGA outperforms other algorithms, including GA, grasshopper optimization algorithm (GOA), particle swarm optimization (PSO), teaching-learning optimization (TLBO), and salp swarm optimization (SSA).
  • The study highlights the importance of feature selection in IDS and demonstrates the effectiveness of the OSMOGA approach in improving detection accuracy and reducing training time.
  • The research was conducted by Soodeh Hosseini and colleagues from the Department of Computer Science, Faculty of Mathematics and Computer Shahid Bahonar University of Kerman Kerman Iran.
  • The study contributes to the development of more effective IDS systems, which is crucial for detecting and preventing cyber-attacks.

Statistics:

  • Classification accuracy rates for OSMOGA on the respective data sets: 98.64% (NSL-KDD), 98.99% (KDD Cup'99), 99.43% (CICIDS2017), and 99.78% (UNSW-NB15).
  • Training time reduction achieved by OSMOGA compared to other algorithms.
  • Number of data sets evaluated in the study: 4.
  • Number of metaheuristic algorithms compared with OSMOGA: 5.

Sources:

  • A Hybrid Method Using Slime Mold Algorithm and Genetic Algorithm for Feature Selection Problems in Intrusion Detection Systems. Engineering Reports, 2025, 7(7): n/a-n/a.
  • https://doi-org.sdpl.idm.oclc.org/10.1002/eng2.70254 (free version of the journal article).
  • NewsRx. Researchers from Department of Computer Science Describe Findings in Engineering (A Hybrid Method Using Slime Mold Algorithm and Genetic Algorithm for Feature Selection Problems in Intrusion Detection Systems). Life Science Weekly. August 12, 2025; p 5863.

Read more