Integrating the DeepSeek-R1 model as an analytical assistant in digital forensic investigations of corruption cases

Hafni Ferdian; Ruki Harwahyu

doi:10.32697/integritas.v11i2.1557

RESEARCH ARTICLE Issue: Vol. 11 No. 2 (2025) | Published: 2025-12-21

Integrating the DeepSeek-R1 model as an analytical assistant in digital forensic investigations of corruption cases

Hafni Ferdian¹ , Ruki Harwahyu²

¹ Universitas Indonesia

² Universitas Indonesia

DOI: https://doi.org/10.32697/integritas.v11i2.1557

READ / PREVIEW FULLTEXT PDF DOWNLOAD FULLTEXT PDF

Downloads

148

Views

164

Citations

8

ABSTRACT

This article examines the integration of the DeepSeek-R1 large language model as an analytical assistant in digital forensic investigations, particularly in corruption cases. The growing volume of digital evidence often leads to substantial analysis backlogs that can extend for months or even years, thereby hindering law enforcement efforts [1]. The use of Artificial Intelligence (AI) and Large Language Models (LLMs) offers the potential to improve investigative efficiency by reducing the burden of processing massive datasets. DeepSeek-R1 is a newly released open-source LLM with advanced reasoning capabilities, achieving performance comparable to state-of-the-art models developed by OpenAI. This study outlines the role of DeepSeek-R1 in supporting digital forensic workflows—from tracing electronic evidence and analyzing data relationships to generating preliminary investigative reports. The methodology includes simulated corruption case experiments comparing investigations assisted by DeepSeek-R1 with conventional manual analysis. The results show that DeepSeek-R1 can accelerate the retrieval of relevant information and produce concise summaries rapidly, significantly reducing analysis time. However, the model remains prone to factual errors (hallucinations) and biases, making human validation by investigators essential. With proper risk mitigation and oversight, integrating DeepSeek-R1 has the potential to significantly enhance the effectiveness of digital forensic investigations in combating corruption.

KEYWORDS

Digital Forensik Kecerdasan Buatan Large Language Model Asisten Investigasi Pemberantasan Korupsi Digital forensics Artificial intelligence Large language model Investigative assistant; Anti-corruption enforcement

AUTHORS & AUTHOR BIOGRAPHY

Hafni Ferdian

, Universitas Indonesia

Electronic Engineering, Universitas Indonesia, Jakarta, Indonesia

Ruki Harwahyu

, Universitas Indonesia

Electronic Engineering, Universitas Indonesia, Jakarta, Indonesia

REFERENCES

Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., & Anadkat, S. (2023). Gpt-4 technical report. In arXiv preprint arXiv:2303.08774. Cornell University. https://doi.org/10.48550/arXiv.2303.08774 Dunsin, D., Ghanem, M. C., Ouazzane, K., & Vassilev, V. (2024). A comprehensive analysis of the role of artificial intelligence and machine learning in modern digital forensics and incident response. Forensic Science International: Digital Investigation, 48, 301675. https://doi.org/10.1016/j.fsidi.2023.301675 Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., & Bi, X. (2025). Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. In arXiv preprint arXiv:2501.12948. https://doi.org/10.48550/arXiv.2501.12948 Henseler, H., & van Beek, H. (2023). ChatGPT as a copilot for investigating digital evidence. Proceedings of the Third International Workshop on Artificial Intelligence and Intelligent Assistance for Legal Professionals in the Digital Workplace (LegalAIIA 2023), 58–69. Kadage, A. D., Nayak, B. M., Vishal Sharad Hingmire, Wanjale, K., Bogiri, N., & Mandale, P. L. (2024). AI-enhanced digital forensics: Automated techniques for efficient investigation and evidence collection. Journal of Electrical Systems, 20(1s), 211–229. https://doi.org/10.52783/jes.766 Michelet, G., & Breitinger, F. (2024). ChatGPT, Llama, can you write my report? An experiment on assisted digital forensics reports written using (local) large language models. Forensic Science International: Digital Investigation, 48, 301683. https://doi.org/10.1016/j.fsidi.2023.301683 Scanlon, M., Breitinger, F., Hargreaves, C., Hilgert, J.-N., & Sheppard, J. (2023). ChatGPT for digital forensic investigation: The good, the bad, and the unknown. Forensic Science International: Digital Investigation, 46, 301609. https://doi.org/10.1016/j.fsidi.2023.301609 Wickramasekara, A., & Scanlon, M. (2024). A framework for integrated digital forensic investigation employing autogen AI agents. 2024 12th International Symposium on Digital Forensics and Security (ISDFS), 1–6. https://doi.org/10.1109/ISDFS60797.2024.10527235

LICENSE AND COPYRIGHT

Open Access Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0)

This work is published open-access and licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

HOW TO CITE

Ferdian, H., & Harwahyu, R. (2025). Integrating the DeepSeek-R1 model as an analytical assistant in digital forensic investigations of corruption cases. Integritas: Jurnal Antikorupsi, 11(2), 255-264. https://doi.org/10.32697/integritas.v11i2.1557