Inhaltszusammenfassung

In today’s digital era, ensuring the privacy and security of data is crucial as large volumes of data are generated and shared. Data privacy, also known as information privacy, involves the proper storage, access, retention, immutability, and security of sensitive data. This includes the appropriate handling of personally identifiable information such as names, addresses, social security numbers, and credit card numbers. Among various data privacy methods, generative adversarial networks (GAN...In today’s digital era, ensuring the privacy and security of data is crucial as large volumes of data are generated and shared. Data privacy, also known as information privacy, involves the proper storage, access, retention, immutability, and security of sensitive data. This includes the appropriate handling of personally identifiable information such as names, addresses, social security numbers, and credit card numbers. Among various data privacy methods, generative adversarial networks (GANs) are one of the recent and advanced approaches for generating realistic synthetic data. GANs enhance data privacy by creating synthetic data that maintains the characteristics of the original data while masking sensitive information, allowing for secure data sharing and analysis. This work systematically reviews existing data synthesis models, focusing on GAN models used for data privacy, compares these methods and models, and discusses their advantages and disadvantages.» weiterlesen» einklappen

Autoren