相关论文: Invisible Entropy: Towards Safe and Efficient Low-…

Recently, text watermarking algorithms for large language models (LLMs) have been proposed to mitigate the potential harms of text generated by LLMs, including fake news and copyright issues. However, current watermark detection algorithms…

Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue,…

LLM watermarks stand out as a promising way to attribute ownership of LLM-generated text. One threat to watermark credibility comes from spoofing attacks, where an unauthorized third party forges the watermark, enabling it to falsely…

Large language models (LLMs) have significantly enhanced the usability of AI-generated code, providing effective assistance to programmers. This advancement also raises ethical and legal concerns, such as academic dishonesty or the…

Protecting intellectual property on LLM-generated code necessitates effective watermarking systems that can operate within code's highly structured, syntactically constrained nature. In this work, we introduce CodeTracer, an innovative…

A generative AI model can generate extremely realistic-looking content, posing growing challenges to the authenticity of information. To address the challenges, watermark has been leveraged to detect AI-generated content. Specifically, a…

As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effective strategy for mitigating such harms by enabling the…

As Generative AI continues to become more accessible, the case for robust detection of generated images in order to combat misinformation is stronger than ever. Invisible watermarking methods act as identifiers of generated content,…

Large language models (LLMs) demonstrate general intelligence across a variety of machine learning tasks, thereby enhancing the commercial value of their intellectual property (IP). To protect this IP, model owners typically allow user…

Recent advancements in watermarking techniques have enabled the embedding of secret messages into AI-generated text (AIGT), serving as an important mechanism for AIGT detection. Existing methods typically interfere with the generation…

Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy…

Large Language Model (LLM) watermarking is crucial for establishing the provenance of machine-generated text, but most existing methods rely on a centralized trust model. This model forces users to reveal potentially sensitive text to a…

In the rapidly evolving domain of artificial intelligence, safeguarding the intellectual property of Large Language Models (LLMs) is increasingly crucial. Current watermarking techniques against model extraction attacks, which rely on…

RAG enables LLMs to easily incorporate external data, raising concerns for data owners regarding unauthorized usage of their content. The challenge of detecting such unauthorized usage remains underexplored, with datasets and methods from…

The increasing deployment of intelligent agents in digital ecosystems, such as social media platforms, has raised significant concerns about traceability and accountability, particularly in cybersecurity and digital content protection.…

With LLM watermarking already being deployed commercially, practical applications increasingly require multibit watermarks that encode more complex payloads, such as user IDs or timestamps, into the generated text. In this work, we propose…

Watermarking involves implanting an imperceptible signal into generated text that can later be detected via statistical tests. A prominent family of watermarking strategies for LLMs embeds this signal by upsampling a (pseudorandomly-chosen)…

Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models (LMs). However, the robustness of the watermarking schemes has not been…

Generative models, especially large language models (LLMs), have shown remarkable progress in producing text that appears human-like. However, they often exhibit patterns that make their output easier to detect than text written by humans.…

To deploy large language models (LLMs) in high-stakes application domains that require substantively accurate responses to open-ended prompts, we need reliable, computationally inexpensive methods that assess the trustworthiness of…