A Confidence-Aware Multi-Layer Framework for Drone Forensic Inference Using Heterogeneous Digital Evidence Sources and Flight Logs Analysis

The increasing use of unmanned aerial vehicles (UAVs) in criminal and adversarial contexts has created new challenges for digital forensic investigations. Current UAV forensic research primarily emphasizes artefact extraction and platform-dependent analysis, while insufficient attention has been given to uncertainty modelling and confidence quantification in forensic inference. This study addresses this methodological gap by proposing a confidence-aware multi-layer UAV forensic framework designed to support legally defensible forensic conclusions. The framework integrates chip-off memory acquisition, logical flight log analysis, companion mobile device artefact examination, and wireless trace correlation within a unified analytical architecture. Physics-based flight trajectory reconstruction and cross-device temporal alignment algorithms enhance reproducibility and platform independence. To reflect varying levels of evidentiary reliability, a structured evidence-weighting approach is introduced alongside a novel Forensic Confidence Index (FCI) that quantifies evidentiary support without implying absolute certainty. Validation using a Yuneec Typhoon Q500 4K dataset demonstrates feasible trajectory reconstruction, temporal correlation, and confidence-constrained attribution under realistic investigative conditions. By explicitly incorporating uncertainty modeling and confidence articulation into UAV forensic workflows, the proposed framework improves scientific rigor, transparency, and legal defensibility while providing a scalable foundation for future cyber-physical forensic investigations.

@article{Parmar2026,
  title     = {A Confidence-Aware Multi-Layer Framework for Drone Forensic Inference Using Heterogeneous Digital Evidence Sources and Flight Logs Analysis},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {2},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Nidhiba Parmar and Naveen Kumar Chaudhary},
  doi       = {10.14569/IJACSA.2026.0170202},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170202}
}