![Fig. 2 shows a code segment illustrating the implementation of the Isolation Forest algorithm for detecting anomalies in blockchain transaction data. It includes the initialization and fitting of the model with specific hyperparameters (n_estimators and contamination) to the scaled data. The code then predicts anomalies, integrating the results into the original DataFrame (Fig. 2). Anomalies are labeled '1' and normal transactions are labeled '0'. Previous research has highlighted the effectiveness of the Isolation Forest algorithm in high-dimensional datasets for detecting anomalies and fraud [14], supporting its use in our study for real-time anomaly detection in blockchain transactions. Validation of proposed solutions. The adequacy of the proposed models was validated using various techniques. The anomaly detection model was assessed through cross-validation to confirm its accuracy and reliability in real-time detection. The NLP approach for smart contract auditing was evaluated by its ability to identify known vulnerabilities in test contracts [15]. The effectiveness of the neural networks for performance optimization was measured by simulating network conditions and quantifying improvements in throughput and latency. Model validation. The validation of the models was performed through various methods. Anomaly detection models were validated using cross-validation metrics such as accuracy, precision, recall, and F1-score. NLP models for smart contract auditing were tested for their ability to identify known vulnerabilities in test contracts. Neural networks for performance optimization were](https://www.researchgate.net/publication/383727485/figure/fig1/AS:11431281275801964@1725446122792/shows-a-code-segment-illustrating-the-implementation-of-the-Isolation-Forest-algorithm_Q320.jpg)
August 2024
·
37 Reads
Eastern-European Journal of Enterprise Technologies
The study focuses on the enhancement of e-voting blockchain network security through the integration of artificial intelligence. The critical problem addressed is the existing limitations in real-time threat detection and anomaly detection within blockchain transactions. These limitations can compromise the integrity and security of blockchain networks, making them vulnerable to attacks and fraudulent activities. The core results of the research include the development and implementation of sophisticated AI algorithms designed to enhance the monitoring of blockchain transactions and the auditing of smart contracts. These AI-driven advancements introduce unique features, such as the capability to detect and respond to security threats and anomalies in real-time. This significantly strengthens and optimizes the security frameworks of blockchain systems in e-voting. These results are explained by the strategic application of machine learning and natural language processing methodologies. By employing these advanced AI techniques, the study has achieved more accurate and efficient threat detection, thereby addressing the security challenges previously mentioned. The practical applications of these findings are extensive and diverse. Enhanced security mechanisms can be utilized in financial transactions, supply chain management, and decentralized applications, providing a robust framework for improved blockchain-based e-voting security. In conclusion, integrating AI into blockchain security mechanisms addresses current limitations in threat detection and offers a scalable and effective solution for future security challenges