Artificial Intelligence in Cybersecurity. Chronicle. Issue 8

Dmitry Namiot

Abstract


This publication opens the eighth edition of a periodic analytical review on the use of Artificial Intelligence (AI) in cybersecurity. This series of materials aims to provide an in-depth study of the rapidly evolving field emerging at the intersection of artificial intelligence and cybersecurity. The key goal of this project is to systematically monitor global trends and summarize the most notable developments. In addition to collecting information, the initiative provides a thorough analysis of legislative initiatives, high-profile incidents, and cutting-edge technological innovations that are shaping the contours of modern cybersecurity under the influence of AI. Each issue of the series has a standardized structure consisting of three sections, ensuring comprehensive coverage of the topic under consideration. The first section focuses on an analysis of the incident database and existing security challenges: it examines real-world attack scenarios, identifies new vulnerabilities, and assesses the threats posed by the introduction of AI algorithms into both defense mechanisms and attacker arsenals. The second section describes the current state of the regulatory environment and the vectors of change. Understanding these processes is of paramount importance, as they define the legal and operational framework within which reliable and secure AI-based systems will need to develop. The third section chronicles scientific and technological advances. Each issue includes an annotated list of the most significant scientific papers—as identified by the authors—expert reports from leading organizations, and descriptions of innovative developments.


Full Text:

PDF (Russian)

References


Egorov, M. Je., et al. "Ob"jasnenija modelej mashinnogo obuchenija i sostjazatel'nye ataki." International Journal of Open Information Technologies 13.9 (2025): 50-59.

Evgrafov, Vladimir Andreevich, Maratovich Nutfullin 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.

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

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, Dmitrij Evgen'evich, Aleksej Aleksandrovich Pichugov, and Andrej Pavlovich Mjakishev. "Kiberataki na zarjadnye stancii." International Journal of Open Information Technologies 13.6 (2025): 147-160.

Namiot, D. E., E. A. Il'jushin, and I. V. Chizhov. "Tekushhie akademicheskie i industrial'nye proekty, posvjashhennye ustojchivomu mashinnomu obucheniju." International Journal of Open Information Technologies 9.10 (2021): 35-46.

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 7." International Journal of Open Information Technologies 14.5 (2026): 43-56.

Kim, Juhee, et al. "SoK: Attack and Defense Landscape of Agentic AI Systems." 35nd USENIX Security Symposium (USENIX Security 26). 2026.

Li, Yiming, et al. "Rethinking the Trigger of Backdoor Attacks: Towards Physical Backdoor Threats." Pattern Recognition (2026): 113665.

D. Namiot, "On the AI Agents Audit Model," 2026 International Russian Smart Industry Conference (SmartIndustryCon), Sochi, Russian Federation, 2026, pp. 404-409, doi: 10.1109/SmartIndustryCon68821.2026.11493110

NIST SP 800-234 High-Performance Computing (HPC) Security Overlay https://csrc.nist.gov/pubs/sp/800/234/final Retrieved: May, 2026

Acharya, Nirajan, and Gaurav Kumar Gupta. "A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms." arXiv preprint arXiv:2604.05969 (2026).

Kuzmenko, Ilya Dmitrievich, Dmitry Evgenyevich Namiot, and Valery Alexandrovich Vasenin. "Metody obnaruzhenija dipfejkov v videokonferencijah v real'nom vremeni." Sovremennye informacionnye tehnologii i IT-obrazovanie 21.2 (2025): 204-220.

Zhang, Haiyue, Yi Nian, and Yue Zhao. "Agent audit: A security analysis system for LLM agent applications." arXiv preprint arXiv:2603.22853 (2026).

Hoi, Mengieong, et al. "SEED: A Large-Scale Benchmark for Provenance Tracing in Sequential Deepfake Facial Edits." arXiv preprint arXiv:2604.10522 (2026).

Paglieri, Davide, et al. "Persona Generators: Generating Diverse Synthetic Personas at Scale." arXiv preprint arXiv:2602.03545 (2026).

Borsukiewicz, Paweł, et al. "Adversarial Camouflage." arXiv preprint arXiv:2603.21867 (2026).

Kuprijanovskij, V. P. Demistifikacija cifrovoj jekonomiki / V. Cifrovaja zheleznaja doroga - prognozy, innovacii, proekty / V. P. Kuprijanovskij, G. V. Sukonnikov, P. M. Bubnov [i dr.] // International Journal of Open Information Technologies. – 2016. – T. 4, # 9. – S. 34-43. – EDN WIQHXX.

Cifrovaja zheleznaja doroga - prognozy, innovacii, proekty / V. P. Kuprijanovskij, G. V. Sukonnikov, P. M. Bubnov [i dr.] // International Journal of Open Information Technologies. – 2016. – T. 4, # 9. – S. 34-43. – EDN WIQHXX.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность Monetec 2026 СНЭ

ISSN: 2307-8162