Blockchain Enhanced Distributed Denial of Service Detection in IoT Using Deep Learning and Evolutionary Computation

Strategic Insights -

Researchers from the Chaitanya Bharathi Institute of Technology have proposed a new framework for detecting Distributed Denial of Service (DDoS) threats in Internet of Things (IoT) environments using advanced techniques. The Metaheuristic-Optimized Blockchain Framework for Attack Detection using a Deep Learning Model (MOBCF-ADDLM) method employs blockchain technology to mitigate DDoS attacks by providing decentralized security solutions. The framework uses data preprocessing, feature selection, and deep belief networks to classify attacks and achieve high classification performance.

Key Takeaways:

  • The MOBCF-ADDLM method is designed to detect DDoS threats in IoT environments using blockchain technology, deep learning, and evolutionary computation techniques.
  • The framework employs decentralized security solutions to mitigate DDoS attacks and provide high classification performance.
  • Data preprocessing utilizes the min-max scaling method to convert input data into a beneficial format.
  • Feature selection is performed using the Aquila optimizer (AO) technique to recognize the most relevant features from input data.
  • The attack classification process employs the deep belief network (DBN) technique to classify attacks.
  • The red panda optimizer (RPO) model modifies the hyper-parameter values of the DBN model optimally to achieve higher classification performance.
  • Experiments were performed under the BoT-IoT Binary and Multiclass datasets, achieving a superior accuracy value of 99.22% over existing models.
  • The MOBCF-ADDLM approach is a novel solution for detecting DDoS threats in IoT environments, utilizing advanced techniques such as blockchain, deep learning, and evolutionary computation.

Statistics:

  • The MOBCF-ADDLM method achieved a superior accuracy value of 99.22% over existing models.
  • The framework utilizes a decentralized security solution to mitigate DDoS attacks.
  • 6 datasets were used in experimental validation of the MOBCF-ADDLM approach.
  • The Research used the BoT-IoT Binary and Multiclass datasets.
  • 99.22% is the accuracy value achieved by the MOBCF-ADDLM approach.

Sources:

  • NewsRx. Chaitanya Bharathi Institute of Technology Reports Findings in Technology (Blockchain enhanced distributed denial of service detection in IoT using deep learning and evolutionary computation). Journal of Engineering. July 14, 2025; p 281.
  • Shivaram, K. M., Research, S. S. B., Shaiju, K., Sathi, S. K., Ammar, K., Ishak, M. K. (2025). Blockchain enhanced distributed denial of service detection in IoT using deep learning and evolutionary computation. Scientific Reports, 15(1), 22537.