Araştırma Makalesi

Adaptive Honeypot Systems via RAG: Enhancing Threat Intelligence with Generative AI

Cilt: 9 Sayı: 2 29 Aralık 2025
PDF İndir
EN TR

Adaptive Honeypot Systems via RAG: Enhancing Threat Intelligence with Generative AI

Öz

Honeypots have long been invaluable resources for intrusion detection and cyber threat intelligence, yet they suffer from an intractable trade-off: low-interaction systems are too artificial, and high-interaction systems pose operational risks and scalability challenges. This paper introduces a new honeypot architecture that uses Retrieval-Augmented Generation (RAG) with the Llama 3.1 8B model to overcome this fidelity–risk dilemma. Instead of running live commands, our system uses a curated database of sanitized command–output pairs for historic Linux commands. When an attacker issues a command, the highest-relevant historic output is recalled and contextualized via Large Language Model (LLM), and the response is empirically informed and dynamically flexible. This architecture maintains realistic interactions without allowing compromise. We built an extensible pipeline spanning data acquisition, preprocessing, retrieval, and response generation, complemented with logging for threat intelligence purposes. Evaluation was performed on six hundred canonical Linux commands using BLEU and ROUGE metrics. Analysis indicates that the RAG-enhanced variant is an order-of-magnitude improvement beyond vanilla LLM setup, with BLEU and ROUGE-L scores rising from 0.04 and 0.24, respectively, to 0.47 and 0.72, respectively. Beyond quantitative fidelity, qualitative analysis indicates that RAG strongly diminishes hallucinations, secures session consistency, and enhances attacker engagement. Extended and more coherent adversary sessions give the defender richer behavioral context with less compromise detection risk. This proposed system illustrates that generative AI, when tied to empirical basis, can achieve high-fidelity deception without operational exposure. Findings demonstrate not only the technical possibility of RAG-based honeypots but also their promise for use in scalable, adaptive, and safe deception resources for both research infrastructures and operational uses.

Anahtar Kelimeler

Large language models, threat intelligence, adaptive honeypot systems

Kaynakça

  1. Morić, Z., Dakić, V., & Regvart, D. (2025). Advancing Cybersecurity with Honeypots and Deception Strategies. Informatics, 12, 1-37.
  2. Javadpour, A., Ja'fari, F., Taleb, T., Shojafar, M., & Benzaïd, C. (2024). A comprehensive survey on cyber deception techniques to improve honeypot performance. Computers & Security, 140, 1-39.
  3. AlQahtan, N., AlOlayan, A., AlAjaji, A., & Almaslukh, A. (2025). HoneyLite: A Lightweight Honeypot Security Solution for SMEs. Sensors, 25, 1-17.
  4. Heluany, J. B. (2024). PLC Honeypots: Enhancing Interaction-Level Assessment. Electronics, 13, 1-18.
  5. Chen, Q., Liu, Y., Tan, R., Jin, Z., Xiao, J., Wang, X., Zhang, F., & Liu, Q. (2025). Shadowkube: Enhancing Kubernetes security with behavioral monitoring and honeypot integration. Cybersecurity, 8, 1-19.
  6. Lanz, S., Pignol, S. L., Schmitt, P., Wang, H., Papaioannou, M., Choudhary, G., & Dragoni, N. (2025). Optimizing Internet of Things Honeypots with Machine Learning: A Review. Applied Sciences, 15, 1-30.
  7. Sezgin, A., & Boyacı, A. (2025). DecoyPot: A large language model-driven web API honeypot for realistic attacker engagement. Computers & Security, 154, 1-9.
  8. Lanka, P., Gupta, K., & Varol, C. (2024). Intelligent Threat Detection—AI-Driven Analysis of Honeypot Data to Counter Cyber Threats. Electronics, 13, 1-28.
  9. Sahraoui, Y., Hadjkouider, A. M., Kerrache, C. A., & Calafate, C. T. (2025). TwinFedPot: Honeypot Intelligence Distillation into Digital Twin for Persistent Smart Traffic Security. Sensors, 25, 1-16.
  10. Visalom, R., Mihăilescu, M., Rughiniș, R., & Țurcanu, D. (2025). Intercepting and Monitoring Potentially Malicious Payloads with Web Honeypots. Future Internet, 17, 1-32.

Kaynak Göster

APA
Sezgin, A. (2025). Adaptive Honeypot Systems via RAG: Enhancing Threat Intelligence with Generative AI. International Journal of Innovative Engineering Applications, 9(2), 175-183. https://doi.org/10.46460/ijiea.1797978
AMA
1.Sezgin A. Adaptive Honeypot Systems via RAG: Enhancing Threat Intelligence with Generative AI. ijiea, IJIEA. 2025;9(2):175-183. doi:10.46460/ijiea.1797978
Chicago
Sezgin, Anıl. 2025. “Adaptive Honeypot Systems via RAG: Enhancing Threat Intelligence with Generative AI”. International Journal of Innovative Engineering Applications 9 (2): 175-83. https://doi.org/10.46460/ijiea.1797978.
EndNote
Sezgin A (01 Aralık 2025) Adaptive Honeypot Systems via RAG: Enhancing Threat Intelligence with Generative AI. International Journal of Innovative Engineering Applications 9 2 175–183.
IEEE
[1]A. Sezgin, “Adaptive Honeypot Systems via RAG: Enhancing Threat Intelligence with Generative AI”, ijiea, IJIEA, c. 9, sy 2, ss. 175–183, Ara. 2025, doi: 10.46460/ijiea.1797978.
ISNAD
Sezgin, Anıl. “Adaptive Honeypot Systems via RAG: Enhancing Threat Intelligence with Generative AI”. International Journal of Innovative Engineering Applications 9/2 (01 Aralık 2025): 175-183. https://doi.org/10.46460/ijiea.1797978.
JAMA
1.Sezgin A. Adaptive Honeypot Systems via RAG: Enhancing Threat Intelligence with Generative AI. ijiea, IJIEA. 2025;9:175–183.
MLA
Sezgin, Anıl. “Adaptive Honeypot Systems via RAG: Enhancing Threat Intelligence with Generative AI”. International Journal of Innovative Engineering Applications, c. 9, sy 2, Aralık 2025, ss. 175-83, doi:10.46460/ijiea.1797978.
Vancouver
1.Anıl Sezgin. Adaptive Honeypot Systems via RAG: Enhancing Threat Intelligence with Generative AI. ijiea, IJIEA. 01 Aralık 2025;9(2):175-83. doi:10.46460/ijiea.1797978