Research on Cooperative Defense Strategy of Swarm Intelligence Awareness Network Based on Bee Colony Algorithm

DOI: https://doi.org/10.62517/jbdc.202501304

Author(s)

Zixuan Wan, Kaiwen Lou

Affiliation(s)

School of Computer Science and Information Technology, Harbin Normal University, Harbin, China

Abstract

The Mobile Crowdsensing (MCS) network is susceptible to large-scale task disruptions and systemic collapses under complex attacks due to limited node resources and generalized attack surfaces. Current collaborative defense technologies are still in their nascent stages, lacking a universal collaboration mechanism, and struggling to support precise threat mitigation in dynamic open environments. This paper proposes a security collaborative defense framework that integrates an ensemble learning algorithm with dynamic policy adjustments and an artificial bee colony algorithm. This framework comprises modules such as data access and sharing, proactive prevention, joint sensing, and collaborative response. The study explores an ensemble learning algorithm with dynamically adjustable collaborative strategies, applying it to an attack event detection model to enhance detection accuracy. Meanwhile, the artificial bee colony-empowered collaborative response mechanism establishes a lightweight communication protocol based on three types of messages (active, updated, and summary). It facilitates cross-entity threat intelligence sharing and strategy coordination through TTL hop limits, focus level thresholds, and dynamic neighborhood reconstruction. A dual-loop response chain is established for homogeneous and heterogeneous entities. Homogeneous entities achieve self-healing through logical isolation, link disconnection, offline scanning and removal, and vulnerability patching. Heterogeneous entities rely on traffic filtering, access control, and feature synchronization to establish a defense-in-depth mechanism.

Keywords

Group Intelligence Perception; Collaborative Defense; Artificial Bee Colony

References

[1] ZHAO G, LI Z, WANG J. Hybrid attacks collaborative defense model using an ensemble honey badger algorithm[J/OL]. Computer Networks, 2025, 261: 111149. [2] YANG Y, LV H, CHEN N. A Survey on ensemble learning under the era of deep learning[J/OL]. Artificial Intelligence Review, 2023, 56(6): 5545-5589. [3] TANG Y, SUN J, WANG H, et al. A Hierarchical Multi-Agent Reinforcement Learning-Based Network Attack-Defense Game and Collaborative Defense Decision-Making Method [J/OL]. Computer & Security, 2024,142:103871. [4] ALREZAAMIRI H, EBRAHIMNEJAD A, MOTAMENI H. Parallel multi-objective artificial bee colony algorithm for software requirement optimization[J/OL]. Requirements Engineering, 2020, 25(3): 363-380. [5] EBRAHIMNEJAD A, TAVANA M, ALREZAAMIRI H. A novel artificial bee colony algorithm for shortest path problems with fuzzy arc weights[J/OL]. Measurement, 2016, 93: 48-56. [6] DI CAPRIO D., EBRAHIMNEJAD A., ALREZAAMIRI H., et al. A novel ant colony algorithm for solving shortest path problems with fuzzy arc weights [J/OL]. Alexandria Engineering Journal, 2022,61(5):3403-3415. [7] ABBASZADEH SORI A, EBRAHIMNEJAD A, MOTAMENI H. Elite artificial bees’ colony algorithm to solve robot’s fuzzy constrained routing problem[J/OL]. Computational Intelligence, 2020, 36(2): 659-681.