PagPassGPT: Pattern Guided Password Guessing via Generative Pretrained Transformer
This work addresses password security vulnerabilities for cybersecurity professionals and researchers, offering incremental improvements over existing models.
The paper tackles the challenges of generating high-quality passwords and reducing duplicates in deep learning-based password guessing by introducing PagPassGPT, a model that incorporates pattern structure information and uses a divide-and-conquer approach, resulting in a 12% increase in correctly guessed passwords and a 25% reduction in duplicates compared to the state-of-the-art.
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.