Developing an Explainable AI System for Digital Forensics: Enhancing Trust and Transparency in Flagging Events for Legal Evidence

Abstract—Advanced forensic approaches are required to handle digital crimes because they need to provide transparent methods that foster trust and enable interpretable evidence in judicial investigations. The current black-box machine learning models deployed in traditional digital forensics tools accomplish their tasks effectively yet fail to meet legal standards for admission in court because they lack proper explainability. This study creates an Explainable Artificial Intelligence (XAI) system for digital forensics to improve flagging events as legal evidence by establishing high levels of trust and transparency. A digital evidence system employs interpretable machine learning models together with investigative analysis techniques for the detection and classification of computer-based irregularities which generate clear explanations of the observed anomalies. The system employs three techniques including SHAP (Shapley Additive Explanations) alongside LIME (Local Interpretable Model-agnostic Explanations) and counterfactual reasoning to deliver understandable explanations about forensic findings thus enhancing investigation clarity for law enforcement agents and attorneys as well as stakeholder professionals. The system performs successfully on actual digital forensic datasets thus boosting investigation speed while minimizing wrong alerts and improving forensic decision explanations. The system must demonstrate GDPR and digital evidence admission framework compliance to maintain legal and ethical correctness for usage in court procedures. Forensic digital investigations need explainable Artificial Intelligence as an essential integration for creating reliable and legally sound practices.

Explainable Artificial Intelligence (XAI), Digital Forensics, SHAP and LIME, Cybercrime Detection, Interpretable Machine Learning

1. Jarrett, A., & Choo, K. K. R. (2021). The impact of automation and artificial intelligence on digital forensics. Wiley Interdisciplinary Reviews: Forensic Science, 3(6), e1418. https://doi.org/10.1002/wfs2.1418 [Google Scholar] [Crossref]

2. Sarker, I. H. (2022). AI-based modeling: Techniques, applications, and research issues towards automation, intelligent, and smart systems. SN Computer Science, 3(2), 158. https://doi.org/10.1007/s42979-022-01056-4 [Google Scholar] [Crossref]

3. Ypma, R. J., Ramos, D., & Meuwly, D. (2023). AI-based forensic evaluation in court: The desirability of explanation and the necessity of validation. Artificial Intelligence in Forensic Science, 2, 2023. https://doi.org/10.1016/j.aifs.2023.01.001 [Google Scholar] [Crossref]

4. Solanke, A. A. (2022). Explainable digital forensics AI: Towards mitigating distrust in AI-based digital forensics analysis using interpretable models. Forensic Science International: Digital Investigation, 42, 301403. https://doi.org/10.1016/j.fsidi.2022.301403 [Google Scholar] [Crossref]

5. Shamoo, Y. (2025). The role of explainable AI (XAI) in forensic investigations. In Digital Forensics in the Age of AI (pp. 31–62). IGI Global Scientific Publishing. [Google Scholar] [Crossref]

6. Hall, S. W., Sakzad, A., & Minagar, S. (2022). A proof of concept implementation of explainable artificial intelligence (XAI) in digital forensics. In International Conference on Network and System Security (pp. 66–85). Cham: Springer. https://doi.org/10.1007/978-3-030-97362-5_5 [Google Scholar] [Crossref]

7. Arthanari, A., Raj, S. S., & Ravindran, V. (2025). A narrative review in application of artificial intelligence in forensic science: Enhancing accuracy in crime scene analysis and evidence interpretation. Journal of International Oral Health, 17(1), 15–22. https://doi.org/10.1007/jioh2025.16 [Google Scholar] [Crossref]

8. Díaz-Rodríguez, N., et al. (2023). Connecting the dots in trustworthy artificial intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulation. Information Fusion, 99, 101896. https://doi.org/10.1016/j.inffus.2023.101896 [Google Scholar] [Crossref]

9. R. de Filippis, R., & Al Foysal, A. (2024). Integrating explainable artificial intelligence (XAI) in forensic psychiatry: Opportunities and challenges. Open Access Library Journal, 11(12), 1–19. https://doi.org/10.4236/oalib.1108199 [Google Scholar] [Crossref]

10. Rai, Y., Saritha, S. K., & Roy, B. N. (2023). Interpreting machine learning models using model-agnostic approach. In AIP Conference Proceedings, 2745(1), 2023. https://doi.org/10.1063/5.0112710 [Google Scholar] [Crossref]

11. Kloosterman, A., et al. (2015). The interface between forensic science and technology: How technology could cause a paradigm shift in the role of forensic institutes in the criminal justice system. Philosophical Transactions of the Royal Society B: Biological Sciences, 370(1674), 20140264. https://doi.org/10.1098/rstb.2014.0264 [Google Scholar] [Crossref]

12. Tiwari, S., Sresth, V., & Srivastava, A. (2020). The role of explainable AI in cybersecurity: Addressing transparency challenges in autonomous defence systems. International Journal of Innovative Research in Science, Engineering and Technology, 9, 718–733. https://doi.org/10.15680/IJIRSET.2020.0904006 [Google Scholar] [Crossref]

13. Hariharan, S., et al. (2021). Explainable artificial intelligence in cybersecurity: A brief review. In Proceedings of the 2021 4th International Conference on Security and Privacy (ISEA-ISAP) (pp. 1–12). https://doi.org/10.1109/ISEAISAP.2021.00015 [Google Scholar] [Crossref]

14. Zhang, J., & Lei, Y. (2022). Trend and identification analysis of anti-investigation behaviour in crime by machine learning fusion algorithm. Wireless Communications and Mobile Computing, 2022, 1761154. https://doi.org/10.1155/2022/1761154 [Google Scholar] [Crossref]

15. Costantini, S., De Gaspers, G., & Olivieri, R. (2019). Digital forensics and investigations meet artificial intelligence. Annals of Mathematics and Artificial Intelligence, 86(1), 193–229. https://doi.org/10.1007/s10462-019-09718-2 [Google Scholar] [Crossref]

16. Charmat, F., et al. (2022). Explainable artificial intelligence for cybersecurity: A literature survey. Annals of Telecommunications, 77(11), 789–812. https://doi.org/10.1007/s12243-021-00891-2 [Google Scholar] [Crossref]

17. Rajapaksha, S., et al. (2023). AI-based intrusion detection systems for in-vehicle networks: A survey. ACM Computing Surveys, 55(11), 1–40. https://doi.org/10.1145/3577049 [Google Scholar] [Crossref]

18. Ibrahim, S., Nazir, S., & Velastin, S. A. (2021). Feature selection using correlation analysis and principal component analysis for accurate breast cancer diagnosis. Journal of Imaging, 7(11), 225.https://doi.org/10.3390/jimaging7110225 [Google Scholar] [Crossref]

19. Ding, H., Chen, L., Dong, L., Fu, Z., & Cui, X. (2022). Imbalanced data classification: A KNN and generative adversarial networks-based hybrid approach for intrusion detection. Future Generation Computer Systems, 131, 240–254. https://doi.org/10.1016/j.future.2022.02.011 [Google Scholar] [Crossref]

20. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953 [Google Scholar] [Crossref]

21. Alsubaei, F. S., Almazroi, A. A., & Ayub, N. (2024). Enhancing phishing detection: A novel hybrid deep learning framework for cybercrime forensics. IEEE Access, 12, 8373–8389. https://doi.org/10.1109/ACCESS.2024.3015764 [Google Scholar] [Crossref]

22. Wu, J. (2017). Introduction to convolutional neural networks. National Key Laboratory of Novel Software Technology, Nanjing University, China, 5(23), 495. https://doi.org/10.1007/s10044-017-0730-0 [Google Scholar] [Crossref]

23. Nanduri, A., & Sherry, L. (2016). Anomaly detection in aircraft data using recurrent neural networks (RNN). In 2016 Integrated Communications Navigation Surveillance (ICNS) (pp. 5C2-1). https://doi.org/10.1109/ICNS.2016.7560545 [Google Scholar] [Crossref]

24. Géron, A. (2022). Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow (2nd ed.). O'Reilly Media. [Google Scholar] [Crossref]

25. Rimal, Y., Sharma, N., & Alsadoon, A. (2024). The accuracy of machine learning models relies on hyperparameter tuning: Student result classification using random forest, randomized search, grid search, bayesian, genetic, and optuna algorithms. Multimedia Tools and Applications, 83(30), 74349–74364. https://doi.org/10.1007/s11042-024-15391-3 [Google Scholar] [Crossref]

26. Hall, S. W., Saksa, A., & Choo, K. K. R. (2022). Explainable artificial intelligence for digital forensics. Wiley Interdisciplinary Reviews: Forensic Science, 4(2), e1434. https://doi.org/10.1002/wfs2.1434 [Google Scholar] [Crossref]

27. Tyagi, A. K., Kumari, S., & Richa. (2024). Artificial intelligence-based cybersecurity and digital forensics: A review. In Artificial Intelligence-Enabled Digital Twin Smart Manufacturing (pp. 391–419). [Google Scholar] [Crossref]

28. Donald, A., & Iqbal, J. (2024). Implementing cyber defense strategies: Evolutionary algorithms, cyber forensics, and AI-driven solutions for enhanced security. [Google Scholar] [Crossref]

29. Tripathy, S. S., & Behera, B. (2024). Evaluation of future perspectives on Snort and Wireshark as tools and techniques for intrusion detection system. SSRN. https://ssrn.com/abstract=5048278 [Google Scholar] [Crossref]

30. Bhattacharya, A. (2022). Applied Machine Learning Explainability Techniques. Packt Publishing. [Google Scholar] [Crossref]

31. Chen, T., et al. (2015). XGBoost: Extreme gradient boosting. R Package Version, 0.4-2(1), 1–4. https://cran.r-project.org/web/packages/xgboost/xgboost.pdf [Google Scholar] [Crossref]

32. Ch, R., Gadepalli, T. R., Abidi, M. H., & Al-Ahmari, A. (2020). Computational system to classify cybercrime offenses using machine learning. Sustainability, 12(10), 4087. https://doi.org/10.3390/su12104087 [Google Scholar] [Crossref]

33. Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30. https://arxiv.org/abs/1705.07874 [Google Scholar] [Crossref]

34. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?" Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135–1144). https://doi.org/10.1145/2939672.2939778 [Google Scholar] [Crossref]

35. Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. Advances in Neural Information Processing Systems, 28. https://arxiv.org/abs/1503.02531 [Google Scholar] [Crossref]

36. Sarma, A. (2021). Cyber forensics in the age of emerging technologies: Deepfakes, IoT, and blockchain. Journal of Digital Forensics & Cyber Security, 7(3), 1–15. https://doi.org/10.1515/jdfcs-2021-0113 [Google Scholar] [Crossref]

• Advanced Digital Communication Strategies: A Comprehensive Analysis
• The Global Impact of Government Censorship on Women’s Access to Information: A Literature Review
• "Reimagining Higher Education Workspaces: A Review on The Transformative Role of Digital Technology Adoption"
• Improved CSP Efficiency: Innovations and Challenges in Thermal Energy Storage Systems
• Thermal Energy Storage in CSP Facilities: A Review of Design Strategies and Economic Considerations