top of page
Search
  • Writer's pictureSarah Dixon

AI bot cracks passwords using leaked data.


AI bot cracks passwords using leaked data.
AI bot cracks passwords using leaked data.

PassGPT is an AI bot developed by researchers from ETH Zürich, Swiss Data Science Center, and SRI International in New York. It is designed to crack passwords by analyzing leaked passwords from various hacks and exploits. The AI tool uses the Generative Pre-trained Transformer 2 (GPT-2) large language model and is built with a unique method of creation called progressive sampling. PassGPT aims to decode the cryptic features ingrained in human-generated passwords and provide users with stronger and more complex passwords while detecting probable passwords according to a set of inputs. This innovation in password cracking demonstrates the potential for AI to improve security measures.

🔐 Introducing PassGPT🔓 Trained on password leaks, PassGPT can generate 20% more unseen passwords than existing GAN methods. 📖 https://t.co/xV3wr4NGCs Joint work with @fperezcruz and @BrilandHitaj. 🧵 Let’s dive into our key contributions. 🧵 — Javi Rando (@javi_rando) June 6, 2023



PassGPT Trained on Millions of Leaked Passwords. AI bot cracks passwords using leaked data.

PassGPT is a password prediction model that has been trained on a vast collection of leaked passwords. It is expected to outperform other models in terms of accuracy.


According to Rando, PassGPT can predict 20% more unseen passwords than the state-of-the-art GAN models, thanks to its training on the RockYou leak. AI bot cracks passwords using leaked data. AI bot cracks passwords using leaked data.


The model employs Generative Adversarial Networks (GANs) to create realistic content that can fool the Discriminator network. With each iteration, both networks learn from their mistakes and improve, resulting in a model that can generate highly realistic passwords.


PassGPT's unique feature is its ability to generate probabilistic passwords, which can help in analyzing password strength vulnerabilities. It can also detect patterns in passwords that may be considered strong by current password strength estimators but are still relatively easy to guess using generative techniques.


PassGPT Can Guess Non-English Passwords As Well

PassGPT has the capacity to learn patterns across multiple languages despite the fact that it is difficult for dictionary-based heuristics to guess passwords written in non-English languages.

“Non-English passwords are hard for dictionary-based heuristics, yet PassGPT learns patterns across multiple languages,” Rando explained.

We reveal patterns that have high probabilities under PassGPT, but are considered strong by state-of-the-art password strength estimators. For example, non-English passwords are hard for dictionary-based heuristics, yet PassGPT learns patterns across multiple languages. — Javi Rando (@javi_rando) June 6, 2023

PassGPT has demonstrated its ability to predict new passwords that were not included in its dataset, indicating the increasing use of AI models across various industries. David Rozado, a data scientist from New Zealand, has developed RightWingGPT, an AI model that supports conservative views, such as gun ownership, while opposing taxes. Rozado plans to create more models, including LeftWingGPT, which will reflect more liberal perspectives, and DepolarizingGPT, which aims to take a "depolarizing" political stance.


Disclaimer: This article is provided for informational purposes only. It is not offered or intended to be used as legal, tax, investment, financial, or other advice.

Comments


bottom of page