Jinghan Jia

Addressing ethical concerns through selective memory removal in AI models.

New dataset enhances evaluation methods for machine unlearning in image generation.

AdvUnlearn enhances image generation safety by combining unlearning with adversarial training.

UGradSL offers a practical solution for removing sensitive information from machine learning models.

Researchers find effective ways to remove unwanted knowledge from language models.

Learn how text watermarking secures your content without altering its meaning.