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.
- gnabgib
What is this spam. No link to today's MIT article[0].. from which most of the sentences and all of the quotes are taken, or the one author Arxiv entry[1]. Quotes as if they talked to the writers.
[0]: https://news.mit.edu/2026/new-method-keeps-kids-safe-from-il... (https://news.ycombinator.com/item?id=48893301)
- liquidise
This reads like a precision vs recall problem.
If I say every model is trained on CSAM, I too will correctly identify 100% of the models that were. Says little about my false positive rate though.
- yk
> The approach, detailed in a paper presented at the International Conference on Machine Learning, achieved 100% accuracy in identifying models specialized for CSAM generation.
I know some reasons for 100% accuracy in machine learning, first of all the test set leaking into training data. Or you just accept a silly high false positive rate.
When I was an admin I liked to joke that if you guarantee more than 5 nines, then you are an insurance company and you are planning to pay the penalty instead of actually fulfilling your promise, here the principle is probably the same.