Artificial Intelligence in Cybersecurity. Chronicle. Issue 7

Dmitry Namiot

Abstract


This article presents the latest (seventh) issue of our regular analytical digest. This series of materials is dedicated to a comprehensive study of the dynamically developing field at the intersection of artificial intelligence (AI) and cybersecurity. The main objective of this initiative is to consistently monitor the global agenda and systematize the most significant events. The project not only collects information but also provides a detailed analysis of legislative innovations, key incidents, and breakthrough technological solutions defining the modern cybersecurity landscape in the context of AI developments.

The structure of each issue in the series is consistent and includes three thematic sections, ensuring comprehensive coverage of the subject area. The first section is devoted to an analysis of the incident base and current threats: it examines practical cases, identifies new vulnerabilities, and assesses the risks associated with the integration of AI algorithms into both security solutions and attack tools. The second section provides an overview of the current state and dynamics of the regulatory framework. Understanding these processes is critically important, as they shape the legal and operational framework within which secure artificial intelligence systems will develop. The third section is devoted to scientific and technological news. Each issue contains an annotated list of the most significant scientific articles, research reports from authoritative organizations, and descriptions of innovative developments, according to the authors.

 


Full Text:

PDF (Russian)

References


Lebedinskij Ju. E., Namiot D. E. Sostjazatel'noe testirovanie bol'shih jazykovyh modelej //International Journal of Open Information Technologies. – 2025. – T. 13. – #. 11. – S. 132-152.

Maloyan N., Ashinov B., Namiot D. Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks //International Journal of Open Information Technologies. – 2025. – T. 13. – #. 9. – S. 1-6.

Maloyan, Narek, and Dmitry Namiot. "Adversarial attacks on llm-as-a-judge systems: Insights from prompt injections." arXiv preprint arXiv:2504.18333 (2025).

Gerasimenko, Denis V., and Dmitry Namiot. "Extracting Training Data: Risks and solutions in the context of LLM security." International Journal of Open Information Technologies 12.11 (2024): 9-19.

Namiot, D. E., E. A. Il'jushin, and I. V. Chizhov. "Osnovanija dlja rabot po ustojchivomu mashinnomu obucheniju." International Journal of Open Information Technologies 9.11 (2021): 68-74.

Namiot, D. E. Shemy atak na modeli mashinnogo obuchenija / D. E. Namiot // International Journal of Open Information Technologies. – 2023. – T. 11, # 5. – S. 68-86. – EDN YVRDOB.

Namiot, D. E., and E. A. Il'jushin. "O kiberriskah generativnogo iskusstvennogo intellekta." International Journal of Open Information Technologies 12.10 (2024): 109-119.

NIST AI 100-2 E2025 https://csrc.nist.gov/pubs/ai/100/2/e2025/final Retrieved: Jan, 2026

Namiot, Dmitry. "Artificial Intelligence in Cybersecurity. Chronicle. Issue 1." International Journal of Open Information Technologies 13.9 (2025): 34-42.

Namiot, Dmitry. "Artificial Intelligence in Cybersecurity. Chronicle. Issue 6." International Journal of Open Information Technologies 14.3 (2026): 76-86.

Li, Hao, et al. "AgentDyn: A Dynamic Open-Ended Benchmark for Evaluating Prompt Injection Attacks of Real-World Agent Security System." arXiv preprint arXiv:2602.03117 (2026).

Kumar, Divyanshu, et al. "Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery." LLM-based Multi-Agent Systems: Towards Responsible, Reliable, and Scalable Agentic Systems. 2026.

Alamsabi, Mohammed, Michael Tchuindjang, and Sarfraz Brohi. "Embedding-Based Detection of Indirect Prompt Injection Attacks in Large Language Models Using Semantic Context Analysis." Algorithms 19.1 (2026): 92.

Bhattarai, Manish, and Minh Vu. "Trustworthy Agentic AI Requires Deterministic Architectural Boundaries." arXiv preprint arXiv:2602.09947 (2026).

Zhou, Zhenhong, et al. "MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents." arXiv preprint arXiv:2602.14281 (2026).

Sun, Xiaobing, and Liangli Zhen. "A Unified Framework for Jailbreak Attacks on Large Language Models." (2026).

Shao, Yangguang, et al. "PromptFuzz: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs." IEEE Transactions on Information Forensics and Security (2026).

Zhang, Tian, et al. "AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification." arXiv preprint arXiv:2602.22724 (2026).

KUZMENKO, Ilya Dmitrievich; NAMIOT, Dmitry Evgenyevich; VASENIN, Valery Alexandrovich. Metody obnaruzhenija dipfejkov v videokonferencijah v real'nom vremeni. Sovremennye informacionnye tehnologii i IT-obrazovanie, v. 21, n. 2, p. 204-220

Siu, Vincent, et al. "A Framework for Formalizing LLM Agent Security." arXiv preprint arXiv:2603.19469 (2026).

Deng, Gelei, et al. "What Makes a Good LLM Agent for Real-world Penetration Testing?." arXiv preprint arXiv:2602.17622 (2026).

Kuprijanovskij, V. P. Demistifikacija cifrovoj jekonomiki / V. P. Kuprijanovskij, D. E. Namiot, S. A. Sinjagov // International Journal of Open Information Technologies. – 2016. – T. 4, # 11. – S. 59-63. – EDN WXQLIJ.

O rabotah po cifrovoj jekonomike / V. P. Kuprijanovskij, D. E. Namiot, S. A. Sinjagov, A. P. Dobrynin // Sovremennye informacionnye tehnologii i IT-obrazovanie. – 2016. – T. 12, # 1. – S. 243-249. – EDN XEQRFJ.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность Monetec 2026 СНЭ

ISSN: 2307-8162