Article
Digital forensic investigation in the age of ChatGPT
Contribution Summary
This editorial examines the impact of ChatGPT on digital forensic investigation, exploring both the benefits and risks of using Large Language Models (LLMs) in this field. The authors discuss the potential applications of LLMs in generating scripts, question answering, multilingual analysis, and automated sentiment analysis, which can expedite and enhance the investigative process. However, they also highlight concerns about bias, errors, and overreliance on these systems, as well as the need for transparency, privacy, and human judgment in their use. The authors also touch on the potential for LLMs to be used in committing crimes and the need for forensic investigation of these systems. The editorial concludes by envisioning a future where digital forensic first responders leverage LLMs to enable natural language querying of digital evidence, potentially leading to a new career specialization: digital forensic prompt engineers.
Keywords: ChatGPT; Large Language Models; Digital Forensic Investigation; Artificial Intelligence; Cybersecurity; Forensic Science; Digital Evidence; Investigation
Abstract
Large Language Models (LLMs), e.g., BERT, GPT-3, GPT-4, LLaMA, etc., have gained public notoriety in recent months with the advent of OpenAI's ChatGPT. Since its public launch in November 2022, professionals across a broad range of disciplines have evaluated its potential implications and disruptions to their respective fields. Schools and universities the world over are discussing the implications of ChatGPT for the trustworthiness of student assignment and exam submissions e and many have already opted to return to traditional pen and paper examinations. This editorial outlined a number of the beneficial use cases and associated risks for the technology in digital forensic investigation.
BibTeX
@article{scanlon2023ChatGPT,
author={Scanlon, Mark and Nikkel, Bruce and Geradts, Zeno},
title="{Digital forensic investigation in the age of ChatGPT}",
journal="{Forensic Science International: Digital Investigation}",
year=2023,
month=03,
volume=44,
publisher={Elsevier},
url={https://doi.org/10.1016/j.fsidi.2023.301543},
doi={https://doi.org/10.1016/j.fsidi.2023.301543},
pages={301543},
abstract={Large Language Models (LLMs), e.g., BERT, GPT-3, GPT-4, LLaMA, etc., have gained public notoriety in recent months with the advent of OpenAI's ChatGPT. Since its public launch in November 2022, professionals across a broad range of disciplines have evaluated its potential implications and disruptions to their respective fields. Schools and universities the world over are discussing the implications of ChatGPT for the trustworthiness of student assignment and exam submissions e and many have already opted to return to traditional pen and paper examinations. This editorial outlined a number of the beneficial use cases and associated risks for the technology in digital forensic investigation.}
}