Inproceedings
Context Based Password Cracking Dictionary Expansion Using Generative Pre-trained Transformers
Contribution Summary
This research focuses on modern password cracking techniques, specifically context-based password cracking and the use of large language models. The authors create context-based password dictionaries by training PassGPT models with contextual information, such as demographics, interests, and hobbies. The effectiveness of this approach is evaluated on ten datasets of leaked passwords from various topics, showing improved password cracking efficiency and accuracy compared to traditional methods. The study contributes to the development of more efficient and effective password cracking tools for law enforcement agencies in digital forensic investigations.
Keywords: password cracking; context-based password cracking; large language models; PassGPT; digital forensics; cybersecurity; machine learning; artificial intelligence
Abstract
With the rise of online criminal activity leading to the increasing importance of digital forensics, efficient and effective password-cracking tools are necessary to collect evidence in a timely manner, leading to solved crimes. Recent advances in machine learning and artificial intelligence have led to the development of context-based and large language model approaches, significantly improving the accuracy and efficiency of password cracking. This work focusses on these more modern techniques, specifically creating context-based contextual password dictionaries through training a series of PassGPTs, a large language model capable of creating password candidates from leaked password dictionary lists. This paper explores possible improvements in password cracking techniques to help law enforcement agencies in digital forensic investigations by combining PassGPT with a contextual approach.
BibTeX
@inproceedings{imhof2024PasswordCrackingGPT,
author={Imhof, Greta and Kanta, Aikaterini and Scanlon, Mark},
title="{Context Based Password Cracking Dictionary Expansion Using Generative Pre-trained Transformers}",
booktitle={2024 Cyber Research Conference - Ireland (Cyber-RCI)},
year=2024,
pages = {},
month=11,
publisher={IEEE},
abstract={With the rise of online criminal activity leading to the increasing importance of digital forensics, efficient and effective password-cracking tools are necessary to collect evidence in a timely manner, leading to solved crimes. Recent advances in machine learning and artificial intelligence have led to the development of context-based and large language model approaches, significantly improving the accuracy and efficiency of password cracking. This work focusses on these more modern techniques, specifically creating context-based contextual password dictionaries through training a series of PassGPTs, a large language model capable of creating password candidates from leaked password dictionary lists. This paper explores possible improvements in password cracking techniques to help law enforcement agencies in digital forensic investigations by combining PassGPT with a contextual approach.}
}