Digital forensics is a critically important area of study dealing with the identification and combating of cyber threats in contemporary networked environments. In this paper, we investigate the possibility of utilizing Large Language Models (LLMs) to examine network traffic categorized as risky according to the University of New South Wales-Network-Based 2015 (UNSW-NB15) dataset. The study employs a multi-phase methodology that combines forensic analysis, evidence extraction, security recommendations, contextual evaluation, and detailed reporting. The results demonstrate high accuracy and qualitative performance across tasks. Automated metrics illustrate the forensic analysis with 95% accuracy, and evidence extraction with 94% precision and 95% coverage. Subjective self-assessment, followed by reviewing 100 examples processed through ChatGPT, shows that outputs have a very high level of clarity (5 out of 5) and relevance (4.5 out of 5). These results highlight the revolutionary role of LLMs in digital forensics with respect to precision, scope, and readability.

[1] Al-Khateeb M., Al-Mousa M.., Al-Sherideh A., Almajali D., Asassfeha M., and Khafajeh H., “Awareness Model for Minimizing the Effects of Social Engineering Attacks in Web Applications,” International Journal of Data and Network Science, vol. 7, no. 2, pp. 791-800, 2023. DOI: 10.5267/j.ijdns.2023.1.010

[2] Al-Milli N., Jobair Z., Al-Mousa M., Alshaikh A., Asassfeh M., Alazaidah R., and Al-Daoud E., “Data Integrity Concerns, Requirements, and Proofing in Cloud Computing,” Journal of Theoretical and Applied Information Technology, vol. 102, no. 12, pp. 5033-5043, 2024. https://jatit.org/volumes/Vol102No12/12Vol102N o12.pdf

[3] Al-Mousa M., “Generic Proactive IoT Cybercrime Evidence Analysis Model for Digital Forensics,” in Proceedings of the International Conference on Information Technology, Amman, pp. 654-659, 2021. https://ieeexplore.ieee.org/document/9491718

[4] Al-Sherideh A., Ismail R., Al-Mousa M., Al- Qawasmi K., Al-Shaikh A., Awwad H., Maabreh K., and Alauthman M., “Development of a Secure Model for Mobile Government Applications in Jordan,” Journal of Statistics Applications and Probability, vol. 13, no. 1, pp. 145-155, 2024. https://digitalcommons.aaru.edu.jo/jsap/vol13/iss 1/10/

[5] Casino F., Dasaklis T., Spathoulas G., Anagnostopoulos M., Ghosal A., Borocz I., and Patsakis C., “Paper Trends, Challenges, and Emerging Topics in Digital Forensics: A Review of Reviews,” IEEE Access, vol. 10, pp. 25464- 25493, 2022. DOI: 10.1109/ACCESS.2022.3154059

[6] Costantini S., De Gasperis G., and Olivieri R., “Digital Forensics and Investigations Meet Artificial Intelligence,” Annals of Mathematics and Artificial Intelligence, vol. 86, no. 1, pp. 193- 229, 2019. https://link.springer.com/article/10.1007/s10472- 019-09632-y

[7] Dragonas E., Lambrinoudakis C., and Nakoutis P., “Forensic Analysis of OpenAI’s ChatGPT Mobile Application,” Forensic Science International: Digital Investigation, vol. 50, pp. 301801, 2024. https://doi.org/10.1016/j.fsidi.2024.301801

[8] Dubey H., Bhatt S., and Negi L., “Digital Forensics Techniques and Trends: A Review,” The International Arab Journal of Information Technology, vol. 20, no. 4, pp. 644-654, 2023. DOI: 10.34028/iajit/20/4/11

[9] Dunsin D., Ghanem M., Ouazzane K., and Vassilev V., “A Comprehensive Analysis of the Role of Artificial Intelligence and Machine Learning in Modern Digital Forensics and Incident Response,” Forensic Science International: Digital Investigation, vol. 48, pp. Agile Proactive Cybercrime Evidence Analysis Model for Digital Forensics 635 301675, 2024. https://doi.org/10.1016/j.fsidi.2023.301675

[10] George J., “Advancing Enterprise Architecture for Post-Merger Financial Systems Integration in Capital Markets laying the Foundation for Machine Learning Application,” Australian Journal of Machine Learning Paper and Applications, vol. 3, no. 2, pp. 429-475, 2023. https://sydneyacademics.com/index.php/ajmlra/ar ticle/view/155

[11] Harpring R., Maghsoudi A., Fikar C., Piotrowicz W., and Heaslip G., “An Analysis of Compounding Factors of Epidemics in Complex Emergencies: A System Dynamics Approach,” Journal of Humanitarian Logistics and Supply Chain Management, vol. 11, no. 2, pp. 198-226, 2021. https://www.emerald.com/insight/content/doi/10. 1108/jhlscm-07-2020-0063/full/html

[12] Hughes J., Chua Y., and Hutchings A., Researching Cybercrimes: Methodologies, Ethics, and Critical Approaches, Palgrave Macmillan, Cham, 2021. https://doi.org/10.1007/978-3-030- 74837-1_10

[13] Husak M., Bartos V., Sokol P., and Gajdos A., “Predictive Methods in Cyber Defense: Current Experience and Paper Challenges,” Future Generation Computer Systems, vol. 115, pp. 517- 530, 2021. https://doi.org/10.1016/j.future.2020.10.006

[14] Jacob L., Thomas K., and Savithri M., Artificial Intelligence for Cyber Defense and Smart Policing, Chapman and Hall/CRC, 2024. https://www.taylorfrancis.com/chapters/edit/10.1 201/9781003251781-4/ai-forensics-lija-jacob- thomas-savithri

[15] Lauriola I., Lavelli A., and Aiolli F., “An Introduction to Deep Learning in Natural Language Processing: Models, Techniques, and Tools,” Neurocomputing, vol. 470, pp. 443-456, 2022. https://doi.org/10.1016/j.neucom.2021.05.103

[16] Malik A., Bhatti D., Park T., Ishtiaq H., Ryou J., and Kim K., “Cloud Digital Forensics: Beyond Tools, Techniques, and Challenges,” Sensors, vol. 24, no. 2, pp. 1-30, 2024. https://doi.org/10.3390/s24020433

[17] Puzis R., Zilberman P., and Elovici Y., “ATHAFI: Agile Threat hunting and Forensic Investigation,” arXiv Preprint, vol. arXiv:2003.03663v1, pp. 1- 12, 2020. https://arxiv.org/pdf/2003.03663

[18] Sharma S., “Digital Forensics: Legal Standards and Practices in Cybercrime Investigation,” in Proceedings of the 4th International Conference on Innovative Practices in Technology and Management, Noida, pp. 1-6, 2024. https://ieeexplore.ieee.org/document/10563327

[19] Stoyanova M., Nikoloudakis Y., Panagiotakis S., Pallis E., and Markakis E., “A Survey on the Internet of Things (IoT) Forensics: Challenges, Approaches, and Open Issues,” IEEE Surveys and Tutorials, vol. 22, no. 2, pp. 1191-1221, 2024. https://ieeexplore.ieee.org/abstract/document/895 0109

[20] Tanner A., Dancer F., Hall J., Parker N., Bishop R., and McBride T., “The Need for Proactive Digital Forensics in Addressing Critical Infrastructure Cyber Attacks,” in Proceedings of the International Conference on Computational Science and Computational Intelligence, Las Vegas, pp. 976-982, 2022. https://ieeexplore.ieee.org/document/10216685

[21] Tok Y. and Chattopadhyay S., “Identifying Threats, Cybercrime and Digital Forensic Opportunities in Smart City Infrastructure Via Threat Modeling,” Forensic Science International: Digital Investigation, vol. 45, pp. 301540, 2023. https://doi.org/10.1016/j.fsidi.2023.301540

[22] Usman N., Usman S., Khan F., Jan M., Sajid A., Alazab M., and Watters P., “Intelligent Dynamic Malware Detection Using Machine Learning in IP Reputation for Forensics Data Analytics,” Future Generation Computer Systems, vol. 118, pp. 124- 141, 2021. https://doi.org/10.1016/j.future.2021.01.004

[23] Wickramasekara A., Breitinger F., and Scanlon M., “Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency,” arXiv Preprint, vol. arXiv:2402.19366v3, pp. 1-20, 2025. https://arxiv.org/pdf/2402.19366