RETRACTED: Optimizing IoT network security: machine learning approaches for smart village intrusion detection
Ranjeet Kumar Panigrahi & Raghvendra Kumar
What the paper says
Purpose This study, a framework, aims to enhance security in smart village environments by leveraging internet of things (IoT)-based data from sensors and IoT-enabled village devices to detect security threats and exploit attack patterns. Design/methodology/approach An effective intrusion detection system (IDS) capable of distinguishing multiple attack types is used. The framework enhances performance through feature selection, which removes irrelevant, redundant and noisy features. A multi-modal architecture is used to efficiently capture complex relationships between cyber-attack data types. Findings Evaluated using publicly available ToN-IoT data sets, the proposed IDS outperformed current state-of-the-art systems in accuracy, precision, detection rate and F1 score. The model demonstrates high accuracy in detecting both known and unknown attacks within the dynamic and evolving IoT networks of smart villages. Originality/value The originality of this framework lies in its application of advanced IDS techniques within the specific context of smart village environments. By focusing on the practical implementation of anomaly detection algorithms, this framework provides valuable insights into their applicability and effectiveness in real-world IoT-based systems.
1 citation
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.00 × 0.4 = 0.00 |
| M · momentum | 0.00 × 0.15 = 0.00 |
| V · venue signal | 0.00 × 0.05 = 0.00 |
| R · text relevance † | 0.00 × 0.4 = 0.00 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.