Continual learning in machine learning systems requires models to adapt and evolve based on new data and experiences. However, this dynamic nature also introduces a vulnerability to data poisoning attacks, where maliciously crafted input can lead to misleading model updates. In this research, we propose a novel approach utilizing the EdDSA encryption system to safeguard the integrity of data streams in continual learning scenarios. By leveraging EdDSA, we establish a robust defense against data poisoning attempts, maintaining the model's trustworthiness and performance over time. Through extensive experimentation on diverse datasets and continual learning scenarios, we demonstrate the efficacy of our proposed approach. The results indicate a significant reduction in susceptibility to data poisoning attacks, even in the presence of sophisticated adversaries.