The goal of this tool is to help users create stronger and more complex passwords. It can also detect possible passwords based on some inputs.
Published Date – 05:49 PM, Sun – 11 June 23
Hyderabad: If there is anything that we learned from ChatGPT and other AI tools that came in the recent past, it is that the Large Language Models (LLM) can be adapted to different concepts. And how using different data sets, tools can be trained to perform various tasks.
One generative AI tool that is pushing the envelope in keeping passwords secure is PassGPT. It is based on ChatGPT’s model and is developed by a team of researchers from ETH Zürich, the Swiss Data Science Center, and SRI International in New York.
The model is trained on millions of passwords that were leaked in various cyberattacks and PassGPT can now generate and guess passwords. It is reportedly better than the state-of-the-art GAN models.
The goal of this tool is to help users create stronger and more complex passwords. It can also detect possible passwords based on some inputs. The model uses a novel technique called progressive sampling, which builds passwords one character at a time, making them harder to crack.
It is also said that the model can compute the probability of any given password and analyse its strength and vulnerabilities. The model can handle passwords in different languages and guess new passwords that are not in its dataset.