VLA-Mark: A cross modal watermark for large vision-language alignment models.

Shuliang Liu Zheng Qi Jesse Jiaxi Xu Yibo Yan Junyan Zhang He Geng Aiwei Liu Peijie Jiang Jia Liu Yik-Cheung Tam Xuming Hu VLA-Mark: A cross modal watermark for large vision-language alignment models. 26409-26427 2025 EMNLP https://doi.org/10.18653/v1/2025.emnlp-main.1342 conf/emnlp/2025 db/conf/emnlp/emnlp2025.html#LiuQXYZGLJLTH25 streams/conf/emnlp