Researchers may have found a way to read images from your mind using artificial intelligence (AI). While the concept is still far from reality, the idea raises privacy concerns.

A Japanese neuroscientist claims to have discovered a new way for AI to decode brain activity into a readable format. The team used machine learning to analyze brain scans of test subjects, feeding up to 10,000 images into an MRI machine.

“Neural interface technology allows recording from a higher number of channels than ever before, allowing us to ‘see’ brain activity in high resolution,” George McConnell, a professor in the Department of Biomedical Engineering at Stevens Institute of Technology who was not involved in the research, told Lifewire in an email interview. “In the case of 1000s of electrode recording sites in the brain, recording action potentials or ‘spikes,’ each recording site is sampling extracellular voltages more than 20,000 times per second. AI is well-suited to these types of massive datasets and has the potential to scan and classify neural activity patterns, i.e., ‘thoughts,’ that the human eye might miss.”

Using AI to decipher thoughts from brain scans has become relatively commonplace. But the new study from Japan is the first time an AI algorithm called Stable Diffusion has been used to elicit images from the brain. The researchers added training to the Stable Diffusion system, adding text descriptions to thousands of photos.