FontGuard: A Robust Font Watermarking Approach Leveraging Deep Font Knowledge

2025-04-04

AI Summary

Existing font watermarking methods neglect font structural and semantic knowledge, resulting in poor visual quality, low embedding capacity, and weak robustness. This paper proposes a robust deep font-knowledge-driven watermarking method: it is the first to jointly leverage font manifold modeling and language-guided vision-language contrastive learning (CLIP) to achieve semantic-level implicit style feature modulation, thereby transcending conventional pixel-level perturbation paradigms; moreover, it enables zero-shot transfer to unseen fonts. Experiments demonstrate significant improvements: decoding accuracy increases by 5.4%, 7.4%, and 5.8% under synthetic distortions, cross-media transmission, and social-platform compression, respectively, while LPIPS-based visual quality improves by 52.7%. The method substantially enhances copyright protection and provenance tracing for AI-generated text.

Technology Category

• Computer Vision: Language and Vision
• Natural Language Processing: Safety and Robustness
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

The proliferation of AI-generated content brings significant concerns on the forensic and security issues such as source tracing, copyright protection, etc, highlighting the need for effective watermarking technologies. Font-based text watermarking has emerged as an effective solution to embed information, which could ensure copyright, traceability, and compliance of the generated text content. Existing font watermarking methods usually neglect essential font knowledge, which leads to watermarked fonts of low quality and limited embedding capacity. These methods are also vulnerable to real-world distortions, low-resolution fonts, and inaccurate character segmentation. In this paper, we introduce FontGuard, a novel font watermarking model that harnesses the capabilities of font models and language-guided contrastive learning. Unlike previous methods that focus solely on the pixel-level alteration, FontGuard modifies fonts by altering hidden style features, resulting in better font quality upon watermark embedding. We also leverage the font manifold to increase the embedding capacity of our proposed method by generating substantial font variants closely resembling the original font. Furthermore, in the decoder, we employ an image-text contrastive learning to reconstruct the embedded bits, which can achieve desirable robustness against various real-world transmission distortions. FontGuard outperforms state-of-the-art methods by +5.4%, +7.4%, and +5.8% in decoding accuracy under synthetic, cross-media, and online social network distortions, respectively, while improving the visual quality by 52.7% in terms of LPIPS. Moreover, FontGuard uniquely allows the generation of watermarked fonts for unseen fonts without re-training the network. The code and dataset are available at https://github.com/KAHIMWONG/FontGuard.

Problem

• Enhances font watermarking quality and capacity using deep learning.
• Improves robustness against real-world distortions and low-resolution fonts.
• Enables watermarking for unseen fonts without network retraining.

Innovation

• Leverages deep font style features
• Uses language-guided contrastive learning
• Generates robust font variants manifold