Contemporary trends in privacy-preserving data pattern recognition
Sergey Vladimirovich Zapechnikov · Procedia Computer Science · 2021
The article is devoted to the recent scientific problem of privacy-preserving data pattern recognition. The purposes of the work are to systematize the security models for such tasks, to identify algorithmic tools that can be used to ensure the privacy of the data processing, and application of models and to analyze the privacy-preserving data pattern recognition systems. The article presents the main concepts and some definitions related to privacy-preserving machine learning, gives a systematization of related problems, and notes modern and promising areas of development of machine learning. Special cryptographic methods and protocols are correlated to the solved problems. A brief description of the known privacy-preserving data pattern recognition systems is given. Unsolved problems in the field of privacy-preserving data pattern recognition are considered.