Tag
Meta is rolling out new AI-powered tools to detect deceptive advertisements on its platforms that appear legitimate but direct users to child sexual abuse material hosted elsewhere online.
MIT researchers developed a technique to audit AI models for their capability to generate child sexual abuse material without producing illegal outputs, achieving 100% accuracy in tests. This method examines hidden model representations to infer whether a model has been fine-tuned for harmful content, providing a scalable way for platforms and law enforcement to detect unsafe models.