# PassGPT: Password Modeling and (Guided) Generation with Large Language Models

arXiv: https://arxiv.org/abs/2306.01545 · HTML: https://mlsanity.com/paper/2306.01545/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 53 references that are in the map.
- First posted on arXiv 2 Jun 2023.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [PassGAN: A Deep Learning Approach for Password Guessing](https://mlsanity.com/paper/1709.00440/) (2017)
- [Improving Password Guessing via Representation Learning](https://mlsanity.com/paper/1910.04232/) (2019)
- [PassFlow: Guessing Passwords with Generative Flows](https://mlsanity.com/paper/2105.06165/) (2021)
- [Reducing Bias in Modeling Real-world Password Strength via Deep Learning and Dynamic Dictionaries](https://mlsanity.com/paper/2010.12269/) (2020)
- [On the Economics of Offline Password Cracking](https://mlsanity.com/paper/2006.05023/) (2020)
- [Interpretable Probabilistic Password Strength Meters via Deep Learning](https://mlsanity.com/paper/2004.07179/) (2020)

## Built on by (most cited first, 8 of 8)

- [LLMs unlock new paths to monetizing exploits](https://mlsanity.com/paper/2505.11449/) (2025)
- [Do You Trust Your Model? Emerging Malware Threats in the Deep Learning Ecosystem](https://mlsanity.com/paper/2403.03593/) (2024)
- [PagPassGPT: Pattern Guided Password Guessing via Generative Pretrained Transformer](https://mlsanity.com/paper/2404.04886/) (2024)
- [PassTSL: Modeling Human-Created Passwords through Two-Stage Learning](https://mlsanity.com/paper/2407.14145/) (2024)
- [MAYA: Addressing Inconsistencies in Generative Password Guessing through a Unified Benchmark](https://mlsanity.com/paper/2504.16651/) (2025)
- [Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques](https://mlsanity.com/paper/2507.13629/) (2025)
- [When Intelligence Fails: An Empirical Study on Why LLMs Struggle with Password Cracking](https://mlsanity.com/paper/2510.17884/) (2025)
- [PassGPT+: Leveraging Linguistic Priors for Password Modeling](https://mlsanity.com/paper/2609.39880/) (2026)

## Abstract (arXiv)

Large language models (LLMs) successfully model natural language from vast amounts of text without the need for explicit supervision. In this paper, we investigate the efficacy of LLMs in modeling passwords. We present PassGPT, a LLM trained on password leaks for password generation. PassGPT outperforms existing methods based on generative adversarial networks (GAN) by guessing twice as many previously unseen passwords. Furthermore, we introduce the concept of guided password generation, where we leverage PassGPT sampling procedure to generate passwords matching arbitrary constraints, a feat lacking in current GAN-based strategies. Lastly, we conduct an in-depth analysis of the entropy and probability distribution that PassGPT defines over passwords and discuss their use in enhancing existing password strength estimators.