Artificial Intelligence in Cybersecurity. Chronicle. Issue 12

Dmitry Namiot

Abstract


This document presents the twelfth installment of a recurring analytical review focused on the application of artificial intelligence (AI) technologies in the field of cybersecurity. This series of publications is designed as a systematic examination of one of the most rapidly evolving domains—a field emerging at the intersection of artificial intelligence and information security. The primary objective of the project is to continuously monitor global trends and synthesize the most significant developments in this area. This involves not only the collection and aggregation of news and information but also a detailed analysis of regulatory frameworks, high-profile incidents, and cutting-edge technological advancements that are shaping the current state of cybersecurity under the growing influence of AI. Each issue in the series follows a consistent structure, comprising three thematic sections that provide a comprehensive approach to the subject matter. The first section reviews security incidents and current challenges; it analyzes real-world attack scenarios, identifies new vulnerabilities, and assesses threats arising from the integration of AI algorithms—both within defensive mechanisms and in the toolkits used by malicious actors. The second section examines the current regulatory landscape and its key development trajectories, as these processes establish the legal and operational conditions necessary for the deployment of reliable and secure AI systems. The third section provides a chronology of scientific and technical progress. Each issue concludes with an annotated list of notable academic publications, analytical reports from leading organizations, and descriptions of innovative products and solutions.


Full Text:

PDF (Russian)

References


Nutfullin, Bulat, Vladimir Evgrafov, and Dmitry Namiot. "Auditing Inference-Time Defense Evaluation for Multimodal Large Language Models." arXiv preprint arXiv:2606.10904 (2026).

Evgrafov, Vladimir Andreevich, Nutfullin Maratovich Bulat, and Dmitrij Evgen'evich Namiot. "Metody atak i zashhity v agentnyh sistemah na osnove bol'shih jazykovyh modelej." International Journal of Open Information Technologies 14.5 (2026): 1-8.

Baryshnikov, F. M. Redkie sobytija v modeljah glubokogo obuchenija / F. M. Baryshnikov, D. E. Namiot // Programmnaja inzhenerija. – 2026. – T. 17, # 5. – S. 239-252. – DOI 10.17587/prin.17.239-252. – EDN LIHEML.

Pichugov, Aleksej Aleksandrovich, Dmitrij Evgen'evich Namiot, and Elena Vasil'evna Zubareva. "Sovremennye metody obuchenija bol'shih jazykovyh modelej s minimumom dannyh: Ot odnogo primera k absoljutnomu nulju–akademicheskij obzor." International Journal of Open Information Technologies 13.6 (2025): 114-124.

Namiot, D. E. "Vvedenie v ataki otravleniem na modeli mashinnogo obuchenija." International Journal of Open Information Technologies 11.3 (2023): 58-68.

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, Dmitry, Eugene Ilyushin, and Ivan Chizhov. "Artificial intelligence and cybersecurity." International Journal of Open Information Technologies 10.9 (2022): 135-147.

Namiot, D. E. O kiberriskah generativnogo Iskusstvennogo Intellekta / D. E. Namiot, E. A. Il'jushin // International Journal of Open Information Technologies. – 2024. – T. 12, # 10. – S. 109-119. – EDN JZCUQS.

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

Namiot, D. E. Iskusstvennyj Intellekt v Kiberbezopasnosti. Hronika. Vypusk 11 / D. E. Namiot // International Journal of Open Information Technologies. – 2026. – T. 14, # 10. – S. 171-184. – EDN KSDGGN.

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

Lebed, S. V., et al. "Large Language Models in Cyberattacks." Doklady Mathematics. Vol. 110. No. Suppl 2. Moscow: Pleiades Publishing, 2024.

Haryati, Barak, and Shaked Zychlinski. "Model-as-a-Trojan: Self-Activating Covert DNS Exfiltration Baked Into the Weights of an LLM Agent." arXiv preprint arXiv:2610.22578 (2026).

Deng, Ailin, and Bryan Hooi. "Graph neural network-based anomaly detection in multivariate time series." Proceedings of the AAAI conference on artificial intelligence. Vol. 35. No. 5. 2021.

Baek, Heewon, et al. "Connecting the Dots in Agentic AI Security: A Cross-Dimensional Threat Taxonomy, Evaluation Maturity, and Open Challenges." arXiv preprint arXiv:2609.23894 (2026).

He, Zheyuan, et al. "A Survey of LLM-Driven Penetration Testing: Taxonomy, Co-Evolution, and Open Challenges." arXiv preprint arXiv:2607.02605 (2026).

Choi, Woohyuk, et al. "Agent Data Injection Attacks are Realistic Threats to AI Agents." arXiv preprint arXiv:2607.05120 (2026).

Tang, Zhenghao, Zhenyu Zang, and Kaifeng Huang. "Benchmarking MCP Vulnerability Detection from a Paired Evaluation Perspective." Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering. 2026.

Agranovskiy, Marat, et al. "Vibe coding in cybersecurity." International Journal of Open Information Technologies 14.10 (2026): 185-197.

Chhabra, Anshuman, et al. "Agentic AI security: Threats, defenses, evaluation, and open challenges." IEEE Access (2026).

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.

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.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность ИТ-КОНГРЕСС ВМК МГУ 2026 СНЭ

ISSN: 2307-8162