MIT's New Method Flags AI Models Trained on CSAM Without Generating It

MIT's New Method Flags AI Models Trained on CASM Without Generating It

Our team at MIT, collaborating with Thorn, developed a breakthrough auditing technique called Gaussian probing. This method identifies if AI models have been fine-tuned to generate child sexual abuse material by analyzing internal adaptations rather than producing images. Achieving 100% accuracy, this approach bypasses legal barriers and psychological risks, offering a scalable solution for platforms like Hugging Face to stop dangerous models before they spread.

"Before, we had no way of measuring this. It was a huge blind spot that some people were taking advantage of. Now, we can address an AI safety problem that is having severe negative impacts."