Personally identifiable information has been found in DataComp CommonPool, one of the largest open-source data sets used to train image generation models. Millions of images of passports, credit cards ...

Microsoft is launching a research project to estimate the influence of specific training examples on the text, images, and other types of media that generative AI models create. That’s per a job ...

Google researchers say they've found a way to reveal some of ChatGPT's training data. The researchers showed certain keywords forced the bot to divulge sections of its training data. In a blogpost, ...