Search

Search Results

• ALGORITHM FOR FILTERING "HINT INJECTIONS" WHEN USING SPATIAL INFORMATION

  S.L. Belyakov , L.А. Izrailev , О.N. Pokusaev

  32-45

  2026-07-07

  Abstract ▼

  The integration of large language models (LLM) into geographic information systems (GIS) opens up new opportunities for spatial analysis, but it is accompanied by specific vulnerabilities such as "hint injection" (prompt injection). Such attacks allow attackers to bypass LLM security mechanisms, manipulate issuance, gain access to confidential information, and violate data integrity. Using space allows you to access an object not directly, but through its spatial relationships with other objects. Existing keyword or template filtering methods do not provide reliable protection due to the constant emergence of new attack scenarios. This determines the relevance of developing adaptive, self-learning algorithms for filtering queries for industrial injections to large language models. The aim of the study is to develop an algorithm for filtering prompt injections for LLM, based on the Case-Based Reasoning (CBR) method. The paper proposes an algorithm for comparing LLM queries with a database of previously known promt injections. The experiment showed that as the database of use cases accumulates, the accuracy of detecting prompt injections increases from 42% to 83%. At the same time, the processing time for a single request increases slightly (from 0.18 to 0.19 seconds with a 23% increase in the database). Approaches to generalizing the precedent base and introspection of the precedent base were also proposed. The proposed algorithm makes it possible to increase the security of LLM-interface systems against prompt injections due to adaptivity and self-learning. The practical significance lies in the possibility of implementing the developed filter into information systems to prevent leaks and manipulation of spatial data. Further research is related to the development of methods for automatic generalization of use cases and the integration of additional contextual analyzers.

• DEVELOPMENT OF A METHODOLOGY FOR INTEGRATING LARGE LANGUAGE MODELS INTO THE PROCESSES OF SECURITY OPERATIONS CENTERS

  V. А. Chastikova , А. S. Bahtin , P.А. Merkulov

  57-69

  2025-10-01

  Abstract ▼

  The article discusses the importance of integrating large language models (LLMs) into information security monitoring center processes (SOCs) to increase their effectiveness in dealing with growing cyber threats. The aim of the research is to develop a method for incorporating LLMs into SOCs aimed at automating data analysis and incident response processes. The research goals include the theoretical justificajustification for and development of a safe LLM implementation platform, as well as assessing existing SOC processes and technical infrastructure. The article analyses key SOC metrics such as average incident detection times and the number of outstanding incidents, and proposes using the GQM approach to improve these metrics.. It also considers the need to assess the risks associated with the use of LLM, taking into account vulnerabilities and threats, as well as methods for minimizing them, including using the OWASP list of critical vulnerabilities. The article suggests the main stages of system development and implementation, including inventory of existing resources, analysis of integration complexity and system deployment. Key aspects such as assessing the complexity of integration, operational and supporting factors, as well as assessing risks associated with introducing new technologies into SOC infrastructure, are considered.
  In conclusion, the relevance of LLM use is emphasized to improve efficiency and quality of SOC work, contributing to increased information security level and faster response to cyberthreats. The introduction of such technologies will allow SOC to not only respond faster to incidents, but also improve the accuracy of data analysis and reduce the risks associated with the human factor

• DEVELOPMENT OF A CHATBOT FOR CLASSIFICATION AND ANALYSIS OF NATURAL LANGUAGE TEXTS USING LOCAL LARGE LANGUAGE MODELS

  Juman Hussain Mohammad , Juman Hussain Mohammad , Y.А. Kravchenko

  159-171

  2025-07-24

  Abstract ▼

  This paper explores local large language models (LLMs) and their application in text classification tasks, while also comparing their performance with traditional methods. The paper provides a comprehensive review of several key local LLMs, with particular focus on their architectural advantages, characteristics, and application domains. Specifically, we examine models with varying numbers of parameters, their ability to adapt to specialized domains, and their computational requirements when deployed on local hardware. Special emphasis is placed on the trade-offs between performance and resource efficiency. As a practical contribution, we developed a chatbot that utilizes local LLMs (such as DeepSeek, Gemma, and Llama2 via Ollama) to classify incoming texts into predefined categories, demonstrating the operation of these models without cloud computing. The system features a modular architecture that allows for easy integration of new models and comparison of their effectiveness. The computational experiment involves evaluating the accuracy and inference speed of local LLMs compared to simpler methods such as Sentence-BERT, TF-IDF and BoWC, highlighting scenarios in which local models outperform or underperform traditional approaches. Testing was conducted using the benchmark BBC dataset. The results show that language models (including 7-billion parameter models) demonstrate strong and logically consistent classification performance in natural language text processing. However, their results are not perfect for benchmark datasets. Notably, we identified cases where all tested models, including traditional methods, misclassified documents, suggesting potential issues with data labeling. These findings indicate the need to reconsider benchmark labels in standard datasets, particularly for domains with subjective categories where expert evaluations may vary significantly. On the other hand, while local LLMs lag behind cloud-based solutions in speed, their advantages in data privacy and offline operation make them suitable for specialized tasks. This is particularly valuable in medical and financial institutions where protection of sensitive information is critical, and where local models can be fine-tuned for specific business processes without the constraints of cloud APIs.