PagPassGPT: Pattern Guided Password Guessing via Generative Pretrained Transformer

TL;DR

PagPassGPT leverages pattern guidance and a divide-and-conquer strategy with GPT to improve password guessing accuracy and reduce duplicates, outperforming existing models.

Contribution

Introduces PagPassGPT, a novel pattern-guided password guessing model with D&C-GEN to decrease duplicate passwords and enhance hit rate.

Findings

Correctly guesses 12% more passwords than state-of-the-art.

Produces 25% fewer duplicate passwords.

Utilizes pattern structure information for improved guessing.

Abstract

Amidst the surge in deep learning-based password guessing models, challenges of generating high-quality passwords and reducing duplicate passwords persist. To address these challenges, we present PagPassGPT, a password guessing model constructed on Generative Pretrained Transformer (GPT). It can perform pattern guided guessing by incorporating pattern structure information as background knowledge, resulting in a significant increase in the hit rate. Furthermore, we propose D&C-GEN to reduce the repeat rate of generated passwords, which adopts the concept of a divide-and-conquer approach. The primary task of guessing passwords is recursively divided into non-overlapping subtasks. Each subtask inherits the knowledge from the parent task and predicts succeeding tokens. In comparison to the state-of-the-art model, our proposed scheme exhibits the capability to correctly guess 12% more passwords while producing 25% fewer duplicates.