Artificial Intelligence in Cybersecurity. Chronicle. Issue 3
Abstract
In this document, we present our third monthly review of current events related to the general topic of using Artificial Intelligence (AI) in cybersecurity. This regularly published document describes regulatory documents, events, and new developments in this field. Currently, we focus on these three aspects. First, these are incidents related to the use of AI in cybersecurity. For example, newly disclosed attacks on machine learning models, identified vulnerabilities and risks in generative AI, etc. Second, these are regulatory documents and new global and local standards related to various aspects of AI in cybersecurity. And third, each review includes new, interesting publications in this area. Naturally, all materials selected for each issue reflect the views and preferences of the authors. This article presents the third edition of our Chronicle of AI in Cybersecurity.
Full Text:
PDF (Russian)References
Namiot, D. E., E. A. Il'jushin, and I. V. Chizhov. "Iskusstvennyj intellekt i kiberbezopasnost'." International Journal of Open Information Technologies 10.9 (2022): 135-147.
Namiot, D. E., and E. A. Il'jushin. "O kiberriskah generativnogo iskusstvennogo intellekta." International Journal of Open Information Technologies 12.10 (2024): 109-119.
Namiot, Dmitry. "Artificial Intelligence in Cybersecurity. Chronicle. Issue 1." International Journal of Open Information Technologies 13.9 (2025): 34-42.
Malicious MCP https://www.koi.ai/blog/postmark-mcp-npm-malicious-backdoor-email-theft Retrieved: Oct, 2025
Namiot, D. E., and E. A. Il'jushin. "Ujazvimosti jekosistemy MCP." International Journal of Open Information Technologies 13.10 (2025): 74-82.
Command Injection Flaw in Framelink Figma MCP Server Puts Nearly 1 Million Downloads at Risk https://www.koi.ai/blog/command-injection-flaw-in-framelink-figma-mcp-server-puts-nearly-1-million-downloads-at-risk Retrieved: Oct, 2025
Shiny tools, shallow checks: how the AI hype opens the door to malicious MCP servers https://securelist.com/model-context-protocol-for-ai-integration-abused-in-supply-chain-attacks/117473/ Retrieved: Oct, 2025
The Month of AI Bugs https://monthofaibugs.com/ Retrieved: Oct, 2025
Embrace The Red https://embracethered.com/blog/index.html Retrieved: Oct, 2025
Detecting Exposed LLM Servers: A Shodan Case Study on Ollama https://blogs.cisco.com/security/detecting-exposed-llm-servers-shodan-case-study-on-ollama Retrieved: Oct, 2025
ZipLine Campaign: A Sophisticated Phishing Attack Targeting US Companies https://research.checkpoint.com/2025/zipline-phishing-campaign/ Retrieved: Oct, 2025
Lebed, S. V., et al. "Large Language Models in Cyberattacks." Doklady Mathematics. Vol. 110. No. Suppl 2. Moscow: Pleiades Publishing, 2024
Namiot, Dmitry. "Artificial Intelligence in Cybersecurity. Chronicle. Issue 2." International Journal of Open Information Technologies 13.10 (2025): 58-67.
Kuzmenko, Ilya Dmitrievich, and Dmitry Evgenyevich Namiot. "Metody obnaruzhenija dipfejkov v videokonferencijah v real'nom vremeni." Sovremennye informacionnye tehnologii i IT-obrazovanie 21.2 (2025).
Prakasha, K. Krishna, and U. Sumalatha. "Privacy-preserving techniques in biometric systems: Approaches and challenges." IEEE Access (2025).
Namiot, Dmitry, and Manfred Sneps-Sneppe. "On Audit and Certification of Machine Learning Systems." 2023 34th Conference of Open Innovations Association (FRUCT). IEEE, 2023.
Namiot, D. E., and E. A. Il'jushin. "Doverennye platformy iskusstvennogo intellekta: sertifikacija i audit." International Journal of Open Information Technologies 12.1 (2024): 43-60.
OECD (2025), “Mapping relevant data collection mechanisms for AI training”, OECD Artificial Intelligence Papers, No. 48, OECD Publishing, Paris, https://doi.org/10.1787/3264cd4c-en
Perset, K. and S. Fialho Esposito (2025), “How are AI developers managing risks?: Insights from responses to the reporting framework of the Hiroshima AI Process Code of Conduct”, OECD Artificial Intelligence Papers, No. 45, OECD Publishing, Paris, https://doi.org/10.1787/658c2ad6-en.
Bezopasnost' II-agentov https://abava.blogspot.com/2025/10/blog-post_23.html Retrieved: Oct, 2025
Namiot, D. E. Ataki na sistemy mashinnogo obuchenija - obshhie problemy i metody / D. E. Namiot, E. A. Il'jushin, I. V. Chizhov // International Journal of Open Information Technologies. – 2022. – T. 10, # 3. – S. 17-22. – EDN DZFSKQ.
These psychological tricks can get LLMs to respond to “forbidden” prompts https://arstechnica.com/science/2025/09/these-psychological-tricks-can-get-llms-to-respond-to-forbidden-prompts/ Retrieved: Oct, 2025
Sokhansanj, Bahrad A. "Uncensored AI in the Wild: Tracking Publicly Available and Locally Deployable LLMs." Future Internet (2025).
OWASP AI Testing Guide! https://github.com/OWASP/www-project-ai-testing-guide Retrieved: Oct, 2025
Fernandes T., Magalhães J. P., Alves W. Cybersecurity in Smart Railways: exploring risks, vulnerabilities and mitigation in the data communication services //Green Energy and Intelligent Transportation. – 2025. – S. 100305
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.
Stealthy attack serves poisoned web pages only to AI agents https://www.helpnetsecurity.com/2025/09/05/ai-agents-prompt-injection-poisoned-web/ Retrieved: Oct, 2025
Namiot, Dmitry, and Eugene Ilyushin. "On the Cybersecurity of AI Agents." International Journal of Open Information Technologies 13.9 (2025): 13-24.
Stealthy attack serves poisoned web pages only to AI agents https://www.helpnetsecurity.com/2025/09/05/ai-agents-prompt-injection-poisoned-web/ Retrieved: Oct, 2025
Grigoris Ntousakis, Julian James Stephen, Michael V. Le, Sai Sree Laya Chukkapalli, Teryl Taylor, Ian M. Molloy, and Frederico Araujo. 2025. Securing MCP-based Agent Workflows. In Proceedings of the 4th Workshop on Practical Adoption Challenges of ML for Systems (PACMI '25). Association for Computing Machinery, New York, NY, USA, 50–55. https://doi.org/10.1145/3766882.3767177
Breaking Through: How to Predict, Prevent, and Prevail over the PRC Cyber Threat https://www.boozallen.com/content/dam/home/pdf/cyber/prc-cyber-report.pdf Retrieved: Oct, 2025
Averting a Robot Catastrophe Preparing for Converging Trends in Robotics and Frontier AI https://www.rand.org/pubs/perspectives/PEA3691-7.html Retrieved: Oct, 2025.
Refbacks
- There are currently no refbacks.
Abava Кибербезопасность ИТ конгресс СНЭ
ISSN: 2307-8162