Artificial Intelligence in Maritime Cybersecurity: Dual-Use Applications for Defense and Offense in the Age of Digital Seas

• Autorzy: Cichocki Rafał

Identyfikatory

DOI

10.12716/1001.19.02.34

• Języki publikacji: EN

Abstrakty

EN

The maritime sector’s rapid digital transformation – including the integration of IT and operational technology (OT) systems and the rise of autonomous vessels – has significantly expanded the cyberattack surface[1] . Artificial Intelligence (AI) now plays a dual role in this landscape, acting as both a powerful enabler of cyberattacks and a critical tool for cybersecurity defense [2] . This paper explores current and emerging uses of AI in offensive and defensive cyber operations targeting maritime systems and infrastructure. On the offensive side, threat actors are leveraging AI for sophisticated attacks such as AI-generated spear phishing, polymorphic malware generation, GPS spoofing, and manipulation of industrial control systems (ICS)[3], [4]. On the defensive side, AI is employed in anomaly detection, predictive analytics, autonomous vessel and port monitoring, and other security applications[5]. The paper also examines vulnerabilities of AI itself – including adversarial attacks, data poisoning, and model manipulation – and discusses strategies to enhance maritime cyber resilience. Key strategies include the use of digital twin simulations, AI-driven deception (honeypots), adversarial training, explainable AI, and international cooperation for information sharing. By analyzing both offensive and defensive developments, this study provides a comprehensive perspective on the dual-use nature of AI in shaping the future of maritime cybersecurity.

Słowa kluczowe

EN

Automatic Identification System; AIS; maritime safety; piracy; satellite communications; Global Maritime Distress and Safety System; GMDSS; ship security; cybersecurity; Vessel Management Systems; VMS

• Wydawca: Faculty of Navigation, Gdynia Maritime University
• Czasopismo: TransNav : International Journal on Marine Navigation and Safety of Sea Transportation
• Rocznik: 2025
• Tom: Vol. 19 No. 2
• Strony: 617--623
• Opis fizyczny: Bibliogr. 23 poz., tab.

Twórcy

autor

Cichocki Rafał

• Gdynia Maritime University, Gdynia, Poland

• https://orcid.org/0000-0002-5004-5587

Bibliografia

• [1] R. Fang, R. Bindu, A. Gupta, and D. Kang, “LLM Agents can Autonomously Exploit One-day Vulnerabilities,” Apr. 17, 2024, arXiv: arXiv:2404.08144. doi: 10.48550/arXiv.2404.08144.
• [2] L. Wu, X. Zhong, J. Liu, and X. Wang, “PTGroup: An Automated Penetration Testing Framework Using LLMs and Multiple Prompt Chains,” in Advanced Intelligent Computing Technology and Applications - 20th International Conference, ICIC 2024, Tianjin, China, August 5-8, 2024, Proceedings, Part IX, D.-S. Huang, W. Chen, and J. Guo, Eds., in Lecture Notes in Computer Science, vol. 14870. Springer, 2024, pp. 220–232. doi: 10.1007/978-981-97-5606-3_19.
• [3] I. Durlik, T. Miller, E. Kostecka, and T. Tuński, “Artificial Intelligence in Maritime Transportation: A Comprehensive Review of Safety and Risk Management Applications,” Appl. Sci., vol. 14, no. 18, Art. no. 18, Jan. 2024, doi: 10.3390/app14188420.
• [4] A. Ergasheva, F. Akhmedov, A. Abdusalomov, and W. Kim, “Advancing Maritime Safety: Early Detection of Ship Fires through Computer Vision, Deep Learning Approaches, and Histogram Equalization Techniques,” Fire, vol. 7, p. 84, Mar. 2024, doi: 10.3390/fire7030084.
• [5] E. Kovacs, “OpenAI Says Iranian Hackers Used ChatGPT to Plan ICS Attacks,” SecurityWeek. Accessed: Jun. 10, 2025. [Online]. Available: https://www.securityweek.com/openai-says-iranian-hackers-used-chatgpt-to-plan-ics-attacks/
• [6] “OpenAI details how threat actors are abusing ChatGPT | TechTarget,” Search Security. Accessed: Jun. 10, 2025. [Online]. Available: https://www.techtarget.com/searchsecurity/news/366613512/OpenAI-details-how-threat-actors-are-abusing-ChatGPT
• [7] J. Hazell, “Spear Phishing With Large Language Models,” arXiv.org. Accessed: Jun. 10, 2025. [Online]. Available: https://arxiv.org/abs/2305.06972v3
• [8] F. Heiding, B. Schneier, A. Vishwanath, and J. Bernstein, “Devising and Detecting Phishing: Large Language Models vs. Smaller Human Models”.
• [9] “AI-Powered Phishing Outperforms Elite Cybercriminals in 2025 - Hoxhunt.” Accessed: Jun. 10, 2025. [Online]. Available: https://hoxhunt.com/blog/ai-powered-phishing-vs-humans
• [10] “Maritime needs to prepare for AI-assisted cyberattacks.” Accessed: Jun. 29, 2025. [Online]. Available: https://mykn.kuehne-nagel.com/news/article/maritime-needs-to-prepare-for-aiassisted-cybe-02-Jun-2025
• [11] J. Sims, “BlackMamba: Using AI to Generate Polymorphic Malware.” Accessed: Jun. 10, 2025. [Online]. Available: https://www.hyas.com/blog/blackmamba-using-ai-to-generate-polymorphic-malware
• [12] M. Burgess, “Criminals Have Created Their Own ChatGPT Clones,” Wired. Accessed: Jun. 10, 2025. [Online]. Available: https://www.wired.com/story/chatgpt-scams-fraudgpt-wormgpt-crime/
• [13] “2023 Cyber Trends and Insights in the Marine Environment Report,” United States Coast Guard News. Accessed: Jun. 29, 2025. [Online]. Available: https://www.news.uscg.mil/maritime-commons/Article/3750095/2023-cyber-trends-and-insights-in-the-marine-environment-report/https%3A%2F%2Fwww.news.uscg.mil%2Fmaritime-commons%2FArticle%2F3750095%2F2023-cyber-trends-and-insights-in-the-marine-environment-report%2F
• [14] “Coast Guard Cyber Command releases 2024 CTIME report,” United States Coast Guard News. Accessed: Jul. 05, 2025. [Online]. Available: https://www.news.uscg.mil/maritime-commons/Article/4189739/coast-guard-cyber-command-releases-2024-ctime-report/https%3A%2F%2Fwww.news.uscg.mil%2Fmaritime-commons%2FArticle%2F4189739%2Fcoast-guard-cyber-command-releases-2024-ctime-report%2F
• [15] “AI-Powered ‘BlackMamba’ Keylogging Attack Evades Modern EDR Security.” Accessed: Jun. 10, 2025. [Online]. Available: https://www.darkreading.com/endpoint-security/ai-blackmamba-keylogging-edr-security
• [16] Z. Labs, “Links and materials for Living off Microsoft Copilot,” Zenity Labs. Accessed: Jun. 29, 2025. [Online]. Available: https://labs.zenity.io/p/links-materials-living-off-microsoft-copilot
• [17] “How to Weaponize Microsoft Copilot for Cyberattackers.” Accessed: Jun. 29, 2025. [Online]. Available: https://www.darkreading.com/application-security/how-to-weaponize-microsoft-copilot-for-cyberattackers
• [18] “Iran-Linked CyberAv3ngers Group Uses ChatGPT To Plan Industrial Attacks.” Accessed: Jun. 10, 2025. [Online]. Available: https://thecyberexpress.com/cyberav3ngers-use-chatgpt-to-plan-ics-attacks/
• [19] T. Miller, I. Durlik, E. Kostecka, S. Sokołowska, P. Kozlovska, and R. Zwolak, “Artificial Intelligence in Maritime Cybersecurity: A Systematic Review of AI-Driven Threat Detection and Risk Mitigation Strategies,” Electronics, vol. 14, no. 9, Art. no. 9, Jan. 2025, doi: 10.3390/electronics14091844.
• [20] R. Dharma, “Cydome launches maritime cybersecurity platform,” Ship Technology. Accessed: Jun. 30, 2025. [Online]. Available: https://www.ship-technology.com/news/cydome-maritime-cybersecurity-platform/
• [21] “Complete cybersecurity protection solution, built for maritime,” CYDOME. Accessed: Jun. 30, 2025. [Online]. Available: https://cydome.io/cydome-protect/
• [22] T. Neumann, “Cybersecurity in Maritime Industry,” TransNav Int. J. Mar. Navig. Saf. Od Sea Transp., vol. 18, no. 4, pp. 765–774, Dec. 2024, doi: 10.12716/1001.18.04.02.
• [23] “AI in the Maritime Industry: Revolutionizing Port Traffic Management | LinkedIn.” Accessed: Jun. 10, 2025. [Online]. Available: https://www.linkedin.com/pulse/ai-maritime-industry-revolutionizing-port-traffic-marc-asselin-ajsoe/

Uwagi

Pełne imiona podano na stronie internetowej czasopisma w "Authors in other databases."