Adaptive Privacy-Compliant XAI Dashboards for Role-Aware Forensic Decision Support
Keywords:
Auditability, Compliance-aware AI, Differential privacy, Digital forensics, Explainable Artificial Intelligence (XAI), Forensic decision support, LIMEAbstract
The article proposes a privacy-compliant Explainable Artificial Intelligence (XAI) dashboard for forensic decision support, addressing the critical need for transparent yet secure AI-driven analysis in sensitive legal contexts. The proposed system dynamically adapts explanations to user roles while enforcing differential privacy and workflow compliance, bridging the gap between interpretability and regulatory constraints. At its core, an Adaptive Differential Privacy (ADP) Engine injects noise into feature attributions based on sensitivity, ensuring GDPR-aligned data protection without compromising explanatory utility. Moreover, a Role-Based Explanation Renderer (RBER) tailors outputs to distinct stakeholders, such as junior analysts receiving anonymized insights or legal auditors obtaining natural language summaries with jurisdictional precedents. A Compliance-Aware Workflow Orchestrator further governs data flow through RBAC policies and chain-of-custody rules, enabling auditable transitions across forensic stages. The architecture integrates with conventional AI pipelines, intercepting raw explanations from SHAP or LIME modules and transforming them into role-aware visualizations. Implemented with Rényi differential privacy for tighter bounds and Kafka-based event streaming for auditability, the system advances state-of-the-art XAI dashboards by unifying privacy, explainability, and workflow rigor. Experiments on forensic datasets demonstrate its efficacy in balancing interpretability with compliance, offering a scalable template for high-stakes decision support systems.
References
H. J. D. S. De Queiroz, “Explainable AI in high-stakes forensic decision-making,” in AI in Digital Forensics and Cybercrime Investigation: Methods, Ethics, and Emerging Technologies, H. M. Zangana and M. Omar, Eds. Hershey, PA, USA: IGI Global Scientific Publishing, 2026, pp. 331–362.
J. Huang, Z. Wang, D. Li, and Y. Liu, “The analysis and development of an XAI process on feature contribution explanation,” 2022 IEEE International Conference on Big Data (Big Data), Osaka, Japan, 2022.
J. Yan and S. Yamada, “Learning dual-path soft decision trees for vision prototype XAI,” IEEE Access, vol. 13, pp. 206031–206045, 2025.
M. Billah, “Explainable AI for digital forensics: Ensuring transparency in legal evidence analysis,” Journal of Forensic Science and Research, vol. 9, no. 2, pp. 109–116, 2025.
Intersoft Consulting, “General data protection regulation,” GDPR.eu.
Y. Shamoo, “The role of explainable AI (XAI) in forensic investigations,” in Digital Forensics in the Age of AI, M. Omar and H. M. Zangana, Eds. Hershey, PA, USA: IGI Global Scientific Publishing, 2025, pp. 31–62.
S. W. Hall, A. Sakzad, and S. Minagar, “A proof of concept implementation of explainable artificial intelligence (XAI) in digital forensics,” in Network and System Security (NSS 2022), Lecture Notes in Computer Science, vol. 13787, X. Yuan, G. Bai, C. Alcaraz, and S. Majumdar, Eds. Cham, Switzerland: Springer, 2022, pp. 66–85.
N. H. Phan, X. Wu, H. Hu, and D. Dou, “Adaptive Laplace mechanism: Differential privacy preservation in deep learning,” in Proceeding of 17th IEEE International Conference on Data Mining (ICDM), New Orleans, LA, USA, 2017, pp. 385–394.
E. Weippl, “An approach to role-based access control for digital content,” in Proceedings of International Conference on Information Technology: Coding and Computing (ITCC), Las Vegas, NV, USA, 2001, pp. 290–294.
K. P. Rajasekar and D. Vezhaventhan, “Artificial intelligence revolutionizing legal and forensic practices: A comprehensive analysis,” in Proceedings of 15th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Kamand, India, 2024, pp. 1–12.
S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Advances in Neural Information Processing Systems (NIPS 2017), U. von Luxburg, I. Guyon, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, Eds. Red Hook, NY, USA: Curran Associates, 2017, vol. 30, pp. 4768–4777.
M. R. Zafar and N. Khan, “Deterministic local interpretable model-agnostic explanations for stable explainability,” Machine Learning and Knowledge Extraction, vol. 3, no. 3, pp. 525–541, 2021.
P. Hermosilla, S. Berríos, and H. Allende-Cid, “Explainable AI for forensic analysis: A comparative study of SHAP and LIME in intrusion detection models,” Applied Sciences, vol. 15, no. 13, p. 7329, 2025.
S. S. Iyengar, S. Nabavirazavi, Y. Hariprasad, P. HB, and C. K. Mohan, “Privacy-preserving AI (federated learning) for digital forensics,” in Artificial Intelligence in Practice, Signals and Communication Technology, Cham, Switzerland: Springer, 2025, pp. 161–176.
A. Bhaware, G. Varshney, J. Kour, T. Bishnoi, M. Jain, and D. Sharma, “A privacy preserving context sensitive kernel,” in Proceedings of 2024 ACM Workshop on Wireless Security and Machine Learning (WiseML ’24), Seoul, Republic of Korea, 2024, pp. 20–25.
V. Krishnan, “Human-centered privacy-preserving analytics for digital marketplace platforms,” Testing, Psychometrics, Methodology in Applied Psychology, vol. 33, no. S2, pp. 1–12, 2026.
Z. Khalid, F. Iqbal, and B. C. M. Fung, “Towards a unified XAI-based framework for digital forensic investigations,” Forensic Science International: Digital Investigation, vol. 50, Oct. 2024.
P. K. Myakala, C. Bura, and R. Juma, “Interactive data dashboards: Design principles, best practices, and applications,” Preprint, 2024.
C. Dwork, “Differential privacy: A survey of results,” in Theory and Applications of Models of Computation (TAMC 2008), vol. 4978, M. Agrawal, D.-Z. Du, Z. Duan, and A. Li, Eds. Berlin, Germany: Springer, 2008, pp. 1–19, .
I. Mironov, “Rényi differential privacy,” in Proceedings of 2017 IEEE 30th Computer Security Foundations Symposium (CSF), Santa Barbara, CA, USA, 2017, pp. 263–275.
F. Lécué, “On the role of knowledge graphs in explainable AI,” Semantic Web, vol. 11, no. 1, pp. 41–51, 2020.
M. Saqib, S. Mahdavifar, B. C. M. Fung, and P. Charland, “A comprehensive analysis of explainable AI for malware hunting,” ACM Computing Surveys, vol. 56, no. 12, pp. 1–40, 2024.
A. A. Solanke and M. A. Biasiotti, “Digital forensics AI: Evaluating, standardizing and optimizing digital evidence mining techniques,” KI–Künstliche Intelligenz, vol. 36, no. 2, pp. 143–161, 2022.
E. Gandotra, D. Bansal, and S. Sofat, “Malware analysis and classification: A survey,” Journal of Information Security, vol. 5, no. 2, pp. 56–64, Apr. 2014.
A. Bozorgpanah and V. Torra, “Explainable machine learning models with privacy,” Progress in Artificial Intelligence, vol. 13, pp. 31–50, 2024.
M. R. Sareddy and S. Khan, “Role-based access control, secure multi-party computation, and hierarchical identity-based encryption: Combining AI to improve mobile healthcare security,” in Proceedings of 2024 International Conference on Emerging Research in Computational Science (ICERCS), Coimbatore, India, 2024, pp. 1–5.
F. Naretto, “Explainable AI methods and their interplay with privacy protection,” Ph.D. dissertation, Scuola Normale Superiore, Pisa, Italy, 2023.
J. Zhao, Y. Chen, and W. Zhang, “Differential privacy preservation in deep learning: Challenges, opportunities and solutions,” IEEE Access, vol. 7, pp. 48901–48911, 2019.
R. K. Muppaneni, “Data privacy in the age of AI: How Dynamics 365 handles regulatory challenges,” International Journal of Artificial Intelligence, Data Science, and Machine Learning, vol. 3, no. 4, pp. 159–170, 2022.
C. Panigutti, A. Beretta, D. Fadda, F. Giannotti, D. Pedreschi, A. Perotti, and S. Rinzivillo, “Co-design of human-centered, explainable AI for clinical decision support,” ACM Transactions on Interactive Intelligent Systems, vol. 13, no. 4, pp. 1–35, 2023.
N. E. Wanza, L. N. M., P. Pulletikurty, and A. T., “Privacy-preserving AI for financial fraud detection: A federated learning approach with homomorphic encryption,” in Proceeding of the 2025 3rd International Conference on Sustainable Computing and Data Communication Systems (ICSCDS), Erode, India, 2025, pp. 353–359.
R. Shokri and V. Shmatikov, “Privacy-preserving deep learning,” in Proceeding of the 22nd ACM SIGSAC Conference Computer and Communications Security (CCS ’15), Denver, CO, USA, 2015, pp. 1310–1321.
S. S. Matta and M. Bolli, “Trustworthy AI: Explainability & fairness in large-scale decision systems,” Review of Applied Science and Technology, vol. 2, no. 4, pp. 54–93, 2023.
X. Tang, R. Shin, H. A. Inan, A. Manoel, N. Mireshghallah, Z. Lin, S. Gopi, J. Kulkarni, and R. Sim, “Privacy-preserving in-context learning with differentially private few-shot generation,” in Proceeding International Conference on Learning Representations (ICLR), 2024.
A. Artelt, F. Hinder, V. Vaquet, R. Feldhans, and B. Hammer, “Contrastive explanations for explaining model adaptations,” in Advances in Computational Intelligence: 16th International Work-Conference on Artificial Neural Networks (IWANN 2021), I. Rojas, G. Joya, and A. Català, Eds. Cham, Switzerland: Springer, 2021, vol. 12861, pp. 101–112.
