Amro Abdalla
@amro-abdalla.bsky.social
PhD @Georgetown University | Works on GenAI, Multimodal models, and AI safety.
Reposted by Amro Abdalla
Our new paper demonstrates that removing images of children from training datasets of text-to-image models fails to prevent the misuse of these models to generate child sexual abuse material (AI CSAM). A thread 🧵
December 16, 2025 at 10:29 AM
Our new paper demonstrates that removing images of children from training datasets of text-to-image models fails to prevent the misuse of these models to generate child sexual abuse material (AI CSAM). A thread 🧵