Generative Deep Learning Techniques for Password Generation

TL;DR

This paper explores various deep learning models for password guessing, introducing novel variational autoencoder techniques and providing a comprehensive empirical analysis of their effectiveness on multiple datasets.

Contribution

It presents new generative deep learning models, especially variational autoencoders with advanced sampling capabilities, and offers a thorough empirical comparison of different approaches.

Findings

Variational autoencoders achieve state-of-the-art sampling performance.

Deep neural network models show promising password generation variability.

Different approaches excel in sample uniqueness and generation diversity.

Abstract

Password guessing approaches via deep learning have recently been investigated with significant breakthroughs in their ability to generate novel, realistic password candidates. In the present work we study a broad collection of deep learning and probabilistic based models in the light of password guessing: attention-based deep neural networks, autoencoding mechanisms and generative adversarial networks. We provide novel generative deep-learning models in terms of variational autoencoders exhibiting state-of-art sampling performance, yielding additional latent-space features such as interpolations and targeted sampling. Lastly, we perform a thorough empirical analysis in a unified controlled framework over well-known datasets (RockYou, LinkedIn, Youku, Zomato, Pwnd). Our results not only identify the most promising schemes driven by deep neural networks, but also illustrate the strengths of each approach in terms of generation variability and sample uniqueness.