LATIDIA · Ciberseguridad

HiMark: Marca de agua multibit jerárquica y controlable para modelos de lenguaje grandes

arXiv:2610.30601v1 Tipo de anuncio: nuevo Resumen: Con la rápida adopción de modelos de lenguaje grandes (LLM) en aplicaciones de generación de texto, se ha vuelto cada vez más difícil rastrear el contenido generado y asignar responsi

La noticia

arXiv:2610.30601v1 Announce Type: new Abstract: With the rapid adoption of large language models (LLMs) in text generation applications, it has become increasingly difficult to trace generated content and assign responsibility for its use, raising concerns about provenance, copyright protection, and accountability. Multi-bit watermarking addresses these issues by embedding multi-bit provenance information into generated text, but reliable extraction remains difficult due to sparse per-bit evidence and the trade-off between watermark-extraction accuracy and text quality. To deal with these challenges, we propose HiMark, a hierarchical and controllable multi-bit watermarking framework for LLM-generated text. During watermark embedding, HiMark uses a hierarchical candidate-control mechanism, including initial candidate sampling, layer-wise tournament elimination, support-based refinement, and