# Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency

Canonical URL: https://markscanlon.co/publications/Survey-Large-Language-Models-Digital-Forensics

CSL-JSON: https://markscanlon.co/publications/Survey-Large-Language-Models-Digital-Forensics.csl.json
BibTeX: https://markscanlon.co/publications/Survey-Large-Language-Models-Digital-Forensics.bib
RIS: https://markscanlon.co/publications/Survey-Large-Language-Models-Digital-Forensics.ris

Authors: Akila Wickramasekara; Frank Breitinger; Mark Scanlon
Venue: Forensic Science International: Digital Investigation
Year: 2025
DOI: https://doi.org/10.1016/j.fsidi.2024.301859
PDF: https://markscanlon.co/publications/Survey-Large-Language-Models-Digital-Forensics.pdf
Full text: https://markscanlon.co/publications/Survey-Large-Language-Models-Digital-Forensics.full.md

## Contribution Summary

This paper reviews recent advances in the application of Large Language Models (LLMs) within digital forensics, focusing on established models, methods, and key challenges. The study explores the potential of LLMs in improving digital forensic investigation efficiency, addressing challenges such as bias, explainability, censorship, and resource-intensive infrastructure. A comprehensive literature review highlights the current challenges in digital forensics and the possibilities of incorporating LLMs, with a focus on automation, investigative methods, and efficiency improvements facilitated by LLMs. The paper also discusses the limitations, ethical considerations, and forensic-specific risks associated with the use of LLMs in digital forensics.

## Abstract

The ever-increasing workload of digital forensic labs raises concerns about law enforcement's ability to conduct both cyber-related and non-cyber-related investigations promptly. Consequently, this article explores the potential and usefulness of integrating Large Language Models (LLMs) into digital forensic investigations to address challenges such as bias, explainability, censorship, resource-intensive infrastructure, and ethical and legal considerations. A comprehensive literature review is carried out, encompassing existing digital forensic models, tools, LLMs, deep learning techniques, and the use of LLMs in investigations. The review identifies current challenges within existing digital forensic processes and explores both the obstacles and the possibilities of incorporating LLMs. In conclusion, the study states that the adoption of LLMs in digital forensics, with appropriate constraints, has the potential to improve investigation efficiency, improve traceability, and alleviate the technical and judicial barriers faced by law enforcement entities.