TY - GEN
T1 - A Position-Based Taxonomy of In-Generation Watermarking for Latent Diffusion Models
AU - Wang, Zhongjian
AU - Gai, Keke
AU - Yu, Jing
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2027.
PY - 2027
Y1 - 2027
N2 - Generative artificial intelligence, especially Text-to-Image technology represented by latent diffusion models, has reshaped the landscape of digital content creation but has also raised deep concerns about false information, copyright ownership, and content traceability. Digital watermarking technology, as an imperceptible identification and traceability mechanism, has become a key technical means to achieve AI-generated content (AIGC) governance and copyright protection. This paper presents a systematic review of in-generation watermarking for latent diffusion models and develops a position-based taxonomy according to where watermarks are embedded in the generation pipeline and model architecture. Furthermore, we analyze the adversarial security threats faced by these watermarks and summarize corresponding defense strategies. Finally, we systematize key evaluation dimensions and identify the open challenges currently faced by the technology. This paper serves as a reference to facilitate future research in this field.
AB - Generative artificial intelligence, especially Text-to-Image technology represented by latent diffusion models, has reshaped the landscape of digital content creation but has also raised deep concerns about false information, copyright ownership, and content traceability. Digital watermarking technology, as an imperceptible identification and traceability mechanism, has become a key technical means to achieve AI-generated content (AIGC) governance and copyright protection. This paper presents a systematic review of in-generation watermarking for latent diffusion models and develops a position-based taxonomy according to where watermarks are embedded in the generation pipeline and model architecture. Furthermore, we analyze the adversarial security threats faced by these watermarks and summarize corresponding defense strategies. Finally, we systematize key evaluation dimensions and identify the open challenges currently faced by the technology. This paper serves as a reference to facilitate future research in this field.
KW - AI-generated content
KW - Copyright protection
KW - Digital watermarking
KW - In-generation watermarking
KW - Latent diffusion models
UR - https://www.scopus.com/pages/publications/105045948300
U2 - 10.1007/978-981-92-2852-2_27
DO - 10.1007/978-981-92-2852-2_27
M3 - Conference contribution
AN - SCOPUS:105045948300
SN - 9789819228546
T3 - Lecture Notes in Computer Science
SP - 361
EP - 377
BT - Knowledge Science, Engineering and Management - 19th International Conference, KSEM 2026, Proceedings
A2 - Niu, Jianwei
A2 - Qiu, Meikang
A2 - Cao, Cungen
PB - Springer Science and Business Media Deutschland GmbH
T2 - 19th International Conference on Knowledge Science, Engineering and Management, KSEM 2026
Y2 - 17 July 2026 through 19 July 2026
ER -