Zhang, L. and Zeng, L. 2026. MSAT-LDM: Toward Transferable High-Fidelity Watermarking for Latent Diffusion Model via Modular Self-Augmented Training. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 42 (Mar. 2026), 36048–36056. DOI:https://doi.org/10.1609/aaai.v40i42.40921.