Языковые модели и онтологии, угрозы безопасности в распределенной системе
Работая с нашим сайтом, вы даете свое согласие на использование файлов cookie. Это необходимо для нормального функционирования сайта, показа целевой рекламы и анализа трафика. Статистика использования сайта отправляется в «Яндекс» и «Google»
Научный журнал Моделирование, оптимизация и информационные технологииThe scientific journal Modeling, Optimization and Information Technology
Online media
issn 2310-6018

Language models and ontologies, security threats in distributed system

Donskikh N.I. 

UDC 004.056.5
DOI: 10.26102/2310-6018/2024.46.3.016

  • Abstract
  • List of references
  • About authors

Research in the field of large language models and natural language processing systems has intensified due to the emergence of new, latent and serious risks, for example, violations of the output generation processes, malicious requests in automatic mode. Synergistic scenarios for large language models are being developed. The main hypothesis taken into account in this study is the possibility of insurance (with a given probability) from the generation of prohibited content and its "mixing" with the user query, taking into account ontological properties and connections to improve the quality of search in practical tasks, for example, using an ontology library. Methods of analysis-synthesis, modeling-forecasting, expert-heuristic, probability theory and decision-making were used. The main results of the article: 1) analytics on the problems of applying large language models in achieving stability in the system infrastructure (a table of key methods was proposed); 2) a language model of network infrastructure stability based on estimates of distributions when mixing words is proposed, which uses the Bayesian method; 3) a similar language model was proposed and studied on the basis of an expert-heuristic approach to assessing risks (uncertainties in the system), in particular, using an information-entropy approach. Research can be developed by complicating models (hypotheses) and the "depth" of risk accounting.

Keywords: large language models, resilience, risks, information security, governance

For citation: Donskikh N.I. Language models and ontologies, security threats in distributed system. Modeling, Optimization and Information Technology. 2024;12(3). URL: https://moitvivt.ru/ru/journal/pdf?id=1634 DOI: 10.26102/2310-6018/2024.46.3.016 (In Russ).

271

Full text in PDF

Received 17.07.2024

Revised 30.07.2024

Accepted 02.08.2024

Published 30.09.2024