Extracting Training Data from ChatGPT

not-just-memorization.github.io · 3,603 words · saved by 2 readers

We have just released a paper that allows us to extract several megabytes of ChatGPT’s training data for about two hundred dollars. (Language models, like ChatGPT, are trained on data taken from the public internet. Our attack shows that, by querying the model, we can actually extract some of the exact data it was trained on.) We estimate that it would be possible to extract ~a gigabyte of ChatGPT’s training dataset from the model by spending more money querying the model.

Extracting Training Data from ChatGPT We have just released a paper that allows us to extract several megabytes of ChatGPT’s training data for about two hundred dollars. (Language models, like ChatGPT, are trained on data taken from the public internet. Our attack shows that, by querying the model, we can actually extract some of the exact data it was trained on.) We estimate that it would be possible to extract ~a gigabyte of ChatGPT’s training dataset from the model by spending more money querying the model. Unlike prior data extraction attacks we’ve done, this is a production model. The key

Extracting Training Data from ChatGPT

saved by

related reading