Artificial Intelligence in Cybersecurity. Chronicle. Issue 9

Dmitry Namiot

Abstract


This publication represents the ninth issue of a periodic analytical review dedicated to the application of artificial intelligence (AI) in cybersecurity. This series of materials focuses on an in-depth study of this dynamically developing field, emerging at the intersection of artificial intelligence and information security technologies. The project's primary objective is to systematically monitor global trends and summarize the most significant developments in this subject area. In addition to aggregating information, the initiative provides a detailed analysis of regulations, high-profile incidents, and advanced technological solutions that shape the modern cybersecurity landscape under the influence of AI.

Each issue in the series has a unified structure, comprising three sections, ensuring comprehensive coverage of the issues under consideration. The first section analyzes the incident database and current security challenges: it examines real-world attack scenarios, identifies new vulnerabilities, and assesses the threats arising from the integration of AI algorithms into both defense mechanisms and attacker tools. The second section describes the current state of the regulatory environment and the main areas of its transformation. Understanding these processes is of paramount importance, as they define the legal and operational parameters within which reliable and secure AI-based systems must develop. The third section chronicles scientific and technological advances. Each issue includes an annotated list of the most significant scientific papers, expert reports from leading organizations, and descriptions of innovative developments, as identified by the authors.


Full Text:

PDF (Russian)

References


Lebedinskiy, Yuriy, and Dmitry Namiot. "Adversarial testing of large language models." International Journal of Open Information Technologies 13.11 (2025): 132-152.

Liu, Hailin, et al. "SafeAgent: A runtime protection architecture for agentic systems." arXiv preprint arXiv:2604.17562 (2026).

Maloyan, Narek, Bislan Ashinov, and Dmitry Namiot. "Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks." International Journal of Open Information Technologies 13.9 (2025): 1-6.

Egorov, M. Je., and D. E. Namiot. "Avtomatizirovannoe obnaruzhenie i klassifikacija konfidencial'nyh dannyh v oblachnyh sredah." International Journal of Open Information Technologies 13.11 (2025): 112-125.

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 8." International Journal of Open Information Technologies 14.6 (2026): 53-64.

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

Si, Mingdan, and Qingshan Li. "Shilling attacks against collaborative recommender systems: a review." The Artificial intelligence review 53.1 (2020): 291-319.

Zhang, Zelin, et al. "From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI." Journal of Information and Intelligence (2026).

Yuan, Y., Jiao, W., Wang, W., Huang, J.t., He, P., Shi, S., Tu, Z., 2023. Gpt-4 is too smart to be safe: Stealthy chat with llms via cipher. arXiv preprint arXiv:2308.06463

Yong, Z.X., Menghini, C., Bach, S.H., 2023. Low-resource languages jailbreak gpt-4. arXiv preprint arXiv:2310.02446.

Jiang, F., Xu, Z., Niu, L., Xiang, Z., Ramasubramanian, B., Li, B., Poovendran, R., 2024. Artprompt: Ascii art-based jailbreak attacks against aligned llms, in: Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers), pp. 15157–15173

Maskey, Utsav, Mark Dras, and Usman Naseem. "Should LLM Safety Be More Than Refusing Harmful Instructions?." arXiv preprint arXiv:2506.02442 (2025).

Namiot, D. E., V. P. Kuprijanovskij, and A. A. Pichugov. "Sostjazatel'nye ataki dlja avtonomnyh transportnyh sredstv." International Journal of Open Information Technologies 12.7 (2024): 139-149.

Namiot, Dmitry. "Artificial Intelligence in Cybersecurity. Chronicle. Issue 7." International Journal of Open Information Technologies 14.5 (2026): 43-55.

Weng, Shihao, et al. "ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection." arXiv preprint arXiv:2605.03378 (2026).

Chen, Zixuan, et al. "IterInject: Indirect Prompt Injection Against LLM Agents via Feedback-Guided Iterative Optimization." arXiv preprint arXiv:2605.24659 (2026).

Qi, Jinhu, et al. "Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security." Academia AI and Applications 2.2 (2026).

Ma, Jianan, et al. "Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions." arXiv preprint arXiv:2605.22321 (2026).

Sakib, Shahnewaz Karim, Swati Kar, and Anindya Bijoy Das. "Adversarial Reframing: A Framework for Targeted Generation in Language Models." arXiv preprint arXiv:2605.21674 (2026).

Kim, Juhee, et al. "Sok: Attack and defense landscape of agentic ai systems." 35nd USENIX Security Symposium (USENIX Security 26). 2026.

Internet cifrovoj zheleznoj dorogi / V. P. Kuprijanovskij, G. V. Sukonnikov, S. A. Sinjagov [i dr.] // International Journal of Open Information Technologies. – 2016. – T. 4, # 12. – S. 53-68. – EDN XETADZ.

Cifrovaja zheleznaja doroga - innovacionnye standarty i ih rol' na primere Velikobritanii / D. E. Nikolaev, V. P. Kuprijanovskij, G. V. Sukonnikov [i dr.] // International Journal of Open Information Technologies. – 2016. – T. 4, # 10. – S. 55-61. – EDN WXBAZN


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность Monetec 2026 СНЭ

ISSN: 2307-8162