English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Large language models (LLMs) have demonstrated outstanding performance,making them valuable digital assets with significant commercial potential.Unfortunately, the LLM and its API are susceptible to intellectual propertytheft. Watermarking is a classic solution for copyright verification. However,most recent emerging LLM watermarking methods focus on identifying AI-generatedtexts rather than watermarking LLM itself. Only a few attempts are based onweight quantification and backdoor watermarking, which are not robust or covertenough, limiting their applicability in practice.  To address this issue, we propose a novel watermarking method for LLMs basedon knowledge injection and innovatively use knowledge as the watermark carrier.Specifically, in the watermark embedding stage, we first embed the watermarksinto the selected knowledge to obtain the watermarked knowledge, subsequentlyinjected into the to-be-protected LLM. In the watermark extraction stage,questions related to the watermarked knowledge are designed, for querying thesuspect LLM and extracting the watermarks from its response. The experimentsshow that the watermark extraction success rate is close to 100% anddemonstrate the effectiveness, fidelity, stealthiness, and robustness of ourproposed method.

Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injection