Unveiling bitcoin network attack using deep reinforcement learning with Boltzmann exploration

This study tackles the critical issue of identifying ransomware transactions within the Bitcoin network. These transactions threaten the stability and security of the cryptocurrency world. Traditional machine learning methods struggle to adapt to the evolving tactics employed by ransomware attackers. They rely on predefined features and metrics, limiting their ability to replicate the adaptability of human analysts. To address this challenge and to address the dynamic nature of fraudulent Bitcoin transactions, we propose a novel approach that incorporates Deep Q-Network (DQN) with Boltzmann exploration model that can autonomously learn and identify evolving attack patterns. The proposed Deep Reinforcement Learning (DRL) offers a more flexible approach by mimicking how security experts learn and adjust their strategies. DQN is a type of reinforcement learning that allows the agent to learn through trial-and-error interactions with the environment. Boltzmann exploration is a technique used to balance exploration (trying new actions) and exploitation (taking actions with the highest expected reward) during the learning process. Proposed DQN model with Boltzmann exploration was evaluated in a simulated environment. This strategy emphasizes the importance of dynamic decision-making for achieving convergence and stability during the learning process, ultimately leading to optimized results. The model achieved a promising validation accuracy of 91% and a strong F1 score demonstrating its ability to generalize effectively to unseen data. This is crucial for real-world applications where encountering entirely new attack scenarios is likely. Compared to alternative exploration techniques like Epsilon-Greedy and Random Exploration, Boltzmann exploration led to superior performance on unseen data. This suggests that the Boltzmann temperature parameter effectively guided the agent's exploration-exploitation trade-off, allowing it to discover valuable patterns applicable to new datasets. In conclusion, our findings demonstrate the potential of DQN with Boltzmann exploration for unsupervised ransomware transaction detection in the Bitcoin network. This approach offers a promising solution for improving the security and resilience of Bitcoin networks against evolving ransomware threats.