• Home
  • Search
  • Digital forensics in law enforcement: A case study of LLM-driven evidence analysis
  • Cite Icon4
  • https://doi.org/10.1016/j.fsidi.2025.301939Copy DOI Icon

Digital forensics in law enforcement: A case study of LLM-driven evidence analysis

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The advent of digital technology and the ubiquity of mobile devices in today's society has led to a significant increase in the importance of mobile forensics in criminal investigations. Responding to the escalating volume and complexity of data due to enhanced smartphone capabilities and pervasive messaging apps, law enforcement agencies face challenges in data analysis. This study explores improving investigative efficiency through LLM-driven analysis of text from mobile messenger communications. We have conducted experiments on anonymized data collected from real crime scenes by employing three state-of-the-art LLM models, namely GPT-4o, Gemini 1.5 and Claude 3.5. The study focuses on optimizing model performance by employing prompt engineering, interpreting expressions embedded with hidden meanings such as slang, and contextually inferring ambiguous word usage. Finally, model performance is quantitatively evaluated using metrics such as precision, recall, F1 score, and hallucination rate. • LLMs analyzed mobile chat data from real criminal case investigations. • GPT-4o, Gemini 1.5, and Claude 3.5 were benchmarked on forensic tasks. • Prompt engineering improved detection of slang and hidden meanings. • Context-based inference helped resolve ambiguous word usage. • Evaluation included precision, recall, F1 score, and hallucination rate.

Similar Papers
  • Book Chapter

Challenges & innovations in digital forensics and cyber investigations

  • Sep 05, 2025
  • Shivankar Anand +5
  • PDF
  • Research Article
  • Citations1

Applying Behavioral Biometrics to Mobile Device Use Measurement in Children: Evaluating the Impact of Training Data Size, Proximity, and Type on Model Performance.

  • Jul 07, 2025
  • Journal of technology in behavioral science
  • Olivia L Finnegan +13
  • Research Article

Strengthening Forensic Science in Bangladesh’s Criminal Justice System: Challenges, Opportunities, and Strategies for Improvement

  • Jan 01, 2025
  • International Journal of Research and Innovation in Social Science
  • Zahurul Islam
  • Research Article
  • Citations5

The Role of Forensic Science and Digital Technology in enhancing Investigation Efficacy: An Analytical Study

  • Jan 10, 2025
  • Cuestiones de Fisioterapia
  • Sruti Bansal,Sanidhya Sadanand Nayak,Ishani Dave
  • Book Chapter
  • Citations65

Chapter 1 - Digital Forensics with Open Source Tools

  • Jan 01, 2011
  • Digital Forensics with Open Source Tools
  • Cory Altheide +1
  • Research Article

Digital Detectives in the Making: Introducing Data Security Through Forensic Challenges

  • Feb 07, 2026
  • Journal of Criminal Justice Education
  • Taylor Fisher +3
  • Research Article
  • Citations28

Open Source Data and Criminal Investigations: Anything You Publish Can and Will Be Used Against You

  • Dec 05, 2014
  • Groningen Journal of International Law
  • Els De Busser
  • Conference Article
  • Citations2

An Adaptive Genetic Algorithm

  • Oct 16, 2012
  • Shihong Wu
  • Research Article

New Paradigm in Legal Research: The Normative Object Approach in Criminal Case Investigation Process

  • Mar 02, 2025
  • Academic Journal of Interdisciplinary Studies
  • Khudzaifah Dimyati +5
  • Research Article
  • Citations27

Research on the Majority Decision Algorithm based on WeChat sentiment classification

  • Jun 14, 2018
  • Journal of Intelligent & Fuzzy Systems
  • Sheng Tai Zhang +3
  • Research Article
  • Citations91

A Survey on Digital Forensics in Internet of Things

  • Sep 19, 2019
  • IEEE Internet of Things Journal
  • Jianwei Hou +3
  • Research Article
  • Citations96

Digital Forensics: Review of Issues in Scientific Validation of Digital Evidence

  • Apr 01, 2018
  • Journal of Information Processing Systems
  • Humaira Arshad +2
  • Peer Review Report

Decision letter: A method for low-coverage single-gamete sequence analysis demonstrates adherence to Mendel’s first law across a large sample of human sperm

  • Apr 19, 2022
  • Molly Przeworski
  • Research Article
  • Citations9

ASSESSING THE EFFECTIVENESS OF LAW ENFORCEMENT IN IMPROVING TAX COMPLIANCE IN INDONESIA: AN EMPIRICAL INVESTIGATION

  • Aug 19, 2021
  • Bulletin of Indonesian Economic Studies
  • Arifin Rosid +1
  • Conference Article

Classifying Credit Card Payment Risk among Senior Citizens using Machine Learning on Limited Data

  • Oct 10, 2025
  • G A M K Jayathilaka +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.