From Learning to Unlearning: Biomedical Security Protection in Multimodal Large Language Models

The security of biomedical Multimodal Large Language Models MLLMs has attracted increasing attention. However, training samples easily contain private information and incorrect knowledge that are difficult to detect, potentially leading to privacy leakage or erroneous outputs after deployment. An...

FragFake: a Dataset for Fine-Grained Detection of Edited Images with Vision Language Models

Fine-grained edited image detection of localized edits in images is crucial for assessing content authenticity, especially given that modern diffusion models and image editing methods can produce highly realistic manipulations. However, this domain faces three challenges: 1 Binary classifiers yie...