Large language models (LLMs) are increasingly integrated into real-world applications through retrieval-augmented generation (RAG) mechanisms to supplement their responses with up-to-date and domain-specific knowledge. However, the valuable and often proprietary nature of the knowledge bases used in RAG introduces the risk of unauthorized usage by adversaries. Existing methods that can be generalized as watermarking techniques to protect these knowledge bases typically involve poisoning attacks. However, these methods require to alter the results of verification samples (\eg, generating incorrect outputs), inevitably making them susceptible to anomaly detection and even introduce new security risks. To address these challenges, we propose \name{} for `harmless' copyright protection of knowledge bases. Instead of manipulating LLM's final output, \name{} implants distinct verification behaviors in the space of chain-of-thought (CoT) reasoning, maintaining the correctness of the final answer. Our method has three main stages: (1) \textbf{Generating CoTs}: For each verification question, we generate two CoTs, including a target CoT for building watermark behaviors; (2) \textbf{Optimizing Watermark Phrases and Target CoTs}: We optimize them to minimize retrieval errors under the black-box setting of suspicious LLM, ensuring that the watermarked verification queries activate the target CoTs without being activated in non-watermarked ones; (3) \textbf{Ownership Verification}: We exploit a pairwise Wilcoxon test to statistically verify whether a suspicious LLM is augmented with the protected knowledge base by comparing its responses to watermarked and benign verification queries. Our experiments on diverse benchmarks demonstrate that \name{} effectively protects knowledge bases against unauthorized usage while preserving the integrity and performance of the RAG.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Lee made the announcement while standing in the middle of Nashville's famed RCA Studio A, a location where legends such as Dolly Parton, Willie Nelson and Charley Pride have all recorded. Packed inside were top music industry leaders, songwriters and lawmakers, all eager to praise the state's rich musical history while also sounding the alarm about the threats AI poses. "Tennessee will be the first state in the country to protect artists' voices with this legislation," Lee said. "And we hope it will be a blueprint for the country."

McGuinness added that the experience would offer the public a "deeper insight into Elvis's life, transporting fans back through the decades to experience his meteoric rise to fame, larger-than-life persona, and the cultural movement he catalysed in the 1950s and 1960s".

At a hearing of the House Intelligence Committee in June 2019, experts warned of the democracy-distorting potential of videos generated by artificial intelligence, known as deepfakes. Chair Adam Schiff (D-California) played a clip spoofing Senator Elizabeth Warren (D-Massachusetts) and called on social media companies to take the threat seriously, because "after viral deepfakes have polluted the 2020 elections, by then it will be too late." Danielle Citron, a law professor then at the University of Maryland, said "deepfake videos and audios could undermine the democratic process by tipping an election." The 2020 campaign is now history. There were upsets, but deepfakes didn't contribute.