To obtain access to full text of journal and articles you must register!
- Article name
- Homomorphic encryption as a tool for reducing operational risks in training machine models on personal data
- Authors
- Pitelinsky K. V., , yekadath@gmail.com, Federal State Autonomous Educational Institution of Higher Education "Moscow Polytechnic University", Moscow, Russia
Ganichev A. A., , alexunderlich@gmail.com, Moscow State Technical University of Civil Aviation, Moscow, Russia
Kalutsky I. V., , kalutsky_igor@mail.ru, Federal State Autonomous Educational Institution of Higher Education "Moscow Polytechnic University", Moscow, Russia
Samsonov A. D., , leha.digdiggggg@gmail.com, Moscow Polytechnic University, Moscow, Russia
Shipulin S. M., , semyon.shipulin@yandex.ru, Moscow Polytechnic University, Moscow, Russia
- Keywords
- information security / homomorphic encryption / operational risks / machine learning / personal data / banking transactions
- Year
- 2025 Issue 2 Pages 3 - 9
- Code EDN
- UJXPHQ
- Code DOI
- 10.52190/2073-2600_2025_2_3
- Abstract
- The article analyzes the use of homomorphic encryption to reduce operational risks using machine learning models on banking transactions. The toolkit includes an open database of regulatory documents, open theoretical information, and data arrays that allow a detailed study of vulnerabilities associated with operational risks, and provides solutions aimed at reducing losses due to risks of this type. The example uses the IBM Transactions for Anti-Money Laundering (AML) array, which contains data on credit card transactions. It discusses why it is precisely the reduction of operational risks that will reduce the amount of material losses in the banking and credit sectors. It demonstrates how data protection using homomorphic encryption will minimize the risks of information leakage, ensure customer privacy, and comply with regulatory requirements that must be observed when working with personal data.
- Text
- BUY for read the full text of article
- Buy
- 500.00 rub
