TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
We introduce TextSeal, a state-of-the-art watermark for large language models. Building on Gumbel-max sampling, TextSeal introduces dual-key generation to restore output diversity, along with entropy-weighted scoring and multi-region localization for improved detection. It supports serving optimizations such as speculative decoding and multi-token prediction, and does not add any inference overhead. TextSeal strictly dominates baselines like SynthID-text in detection strength and is robust to dilution, maintaining confident localized detection even in heavily mixed human/AI documents. The scheme is theoretically distortion-free, and evaluation across reasoning benchmarks confirms that it preserves downstream performance; while a multilingual human evaluation (6000 A/B comparisons, 5 languages) shows no perceptible quality difference. Beyond its use for provenance detection, TextSeal is also ``radioactive'': its watermark signal transfers through model distillation, enabling detection of unauthorized use.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service
Embedding-as-a-Service (EaaS) has become an important semantic infrastructure for natural language and multimedia applications, but it is highly vulnerable to model stealing and copyright infringement. Existing EaaS wate…
High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking
The proliferation of AIGC-driven face manipulation and deepfakes poses severe threats to media provenance, integrity, and copyright protection. Existing versatile watermarking systems typically rely on embedding explicit…
Multi-Agent Framework for Controllable and Protected Generative Content Creation: Addressing Copyright and Provenance in AI-Generated Media
The proliferation of generative AI systems creates unprecedented opportunities for content creation while raising critical concerns about controllability, copyright infringement, and content provenance. Current generativ…
Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning
Federated learning (FL) is vulnerable to multi-level attacks. However, existing methods address them separately, leaving FL exposed to data leakage, unauthorized reuse, and malicious gradient manipulation. In this work, …
Federated LearningOn the Coexistence and Ensembling of Watermarks
Watermarking, the practice of embedding imperceptible information into media such as images, videos, audio, and text, is essential for intellectual property protection, content provenance and attribution. The growing com…