Research on privacy protection technology in computer data science
<p>Zhenhan Tan</p> · Academic Journal of Computing & Information Science · 2024
With the widespread application of big data and artificial intelligence, data privacy issues in computer data science have become increasingly important. This paper reviews the main privacy-preserving technologies, including differential privacy, homomorphic encryption, secure multi-party computation, and federated learning. These techniques offer methods to protect user privacy without compromising data utility. The paper analyzes their fundamental principles, strengths, and weaknesses, and discusses their applications and challenges in fields such as healthcare, finance, social networks, and the Internet of Things (IoT). The study shows that although these technologies significantly enhance data privacy, challenges remain in terms of computational efficiency, scalability, and practical deployment. Finally, the paper explores future trends in privacy-preserving technologies, suggesting further exploration in the areas of technology integration, standardization, and balancing efficiency with security to promote feasibility and adoption in real-world applications. This study aims to provide valuable insights for researchers and practitioners in the field.