NEWS

4756

Discussion on “Deep Learning Methods for Intelligent Analysis of Personal Data while Protecting Confidentiality”

02 December 2019 - 09:46 | Conferences, assemblies

At the plenary session of the 5th Republican Conference, "Actual multidisciplinary scientific and practical problems of information security" the head of department, Ph.D., professor Yadigar Imamverdiyev made a speech.

The head of the department presented a report on "Deep Learning Methods for Intelligent Analysis of Personal Data while Protecting Confidentiality" and said that personal data has become one of the main targets of cybercriminals in recent decades. He said that as a result of the rapid development of information and communication technologies, there are significant threats to the security of personal data generated in large volumes.  Noting that some of these threats are related to the intellectual analysis of personal data, he revealed new sensory knowledge about individuals and social groups by linking and analyzing large-scale personal data collected from various sources.

He said most personal data incidents are related to the transfer of personal data to analytics companies without proper authorization: “Even with the appropriate permission from personal data owners, modern intellectual analysis techniques allow access to sensitive information about individuals and social groups by analyzing and linking data from a variety of sources, despite confidentiality measures. Therefore, privacy protection is one of the most urgent issues in today's Big Data environment.

Speaking about data privacy threats, threats to the disclosure of sensitive or sensitive information, as well as privacy protection, the reporter said that the main purpose of ensuring the confidentiality of data is the protection of personal data.

In his speech, he informed about methods for protecting the personal data confidentiality, intellectual comparative analysis of Deep Learning techniques, as well as the challenges and ways of solutions in-depth training methods with differential privacy, multilateral secure computations, and homomorphic encryption methods.

Imamverdiyev emphasized that the development of technology makes it necessary to revise the legal framework to ensure the security of personal data.

© All rights reserved. Citing to www.ict.az is necessary upon using news