Related papers: Bypassing LLM Watermarks with Color-Aware Substitu…

The integrity of peer review is fundamental to scientific progress, but the rise of large language models (LLMs) has introduced concerns that some reviewers may rely on these tools to generate reviews rather than writing them independently.…

Training data detection is critical for enforcing copyright and data licensing, as Large Language Models (LLM) are trained on massive text corpora scraped from the internet. We present SPECTRA, a watermarking approach that makes training…

Model watermarking utilizes internal representations to protect the ownership of large language models (LLMs). However, these features inevitably undergo complex distortions during realistic model modifications such as fine-tuning,…

Recent advances in the capabilities of large language models such as GPT-4 have spurred increasing concern about our ability to detect AI-generated text. Prior works have suggested methods of embedding watermarks in model outputs, by…

As large language models (LLMs) generate increasingly human-like text, watermarking has emerged as a promising solution for reliable attribution beyond mere detection. While multi-bit watermarking enables richer provenance encoding,…

The recent advancements in large language models (LLMs) have sparked a growing apprehension regarding the potential misuse. One approach to mitigating this risk is to incorporate watermarking techniques into LLMs, allowing for the tracking…

Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data…

A new approach to linguistic watermarking of language models is presented in which information is imperceptibly inserted into the output text while preserving its readability and original meaning. A cross-attention mechanism is used to…

The effectiveness of watermark algorithms in AI-generated text identification has garnered significant attention. Concurrently, an increasing number of watermark algorithms have been proposed to enhance the robustness against various…

Large language models (LLMs) have made fluent essay writing, code drafting, and quiz answering instantly available to students at every level, from secondary school through graduate study. Many educators do not object to LLM use…

We present a publicly-detectable watermarking scheme for LMs: the detection algorithm contains no secret information, and it is executable by anyone. We embed a publicly-verifiable cryptographic signature into LM output using rejection…

Self-supervised learning is an emerging machine learning paradigm. Compared to supervised learning which leverages high-quality labeled datasets, self-supervised learning relies on unlabeled datasets to pre-train powerful encoders which can…

To mitigate the potential misuse of large language models (LLMs), recent research has developed watermarking algorithms, which restrict the generation process to leave an invisible trace for watermark detection. Due to the two-stage nature…

Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in Large Vision-Language Models (LVLMs). However, vision-agnostic watermarks may introduce visually irrelevant tokens and disrupt…

As large language models (LLMs) have advanced rapidly, concerns regarding their safety have become prominent. In this paper, we discover that code-switching in red-teaming queries can effectively elicit undesirable behaviors of LLMs, which…

General large language models (LLMs) such as ChatGPT have shown remarkable success, but it has also raised concerns among people about the misuse of AI-generated texts. Therefore, an important question is how to detect whether the texts are…

Statistical watermarking techniques are well-established for sequentially decoded language models (LMs). However, these techniques cannot be directly applied to order-agnostic LMs, as the tokens in order-agnostic LMs are not generated…

While watermarks for closed LLMs have matured and have been included in large-scale deployments, these methods are not applicable to open-source models, which allow users full control over the decoding process. This setting is understudied…

Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. Based on these LLMs, businesses have started to provide Embeddings-as-a-Service (EaaS), offering feature extraction…

Watermarking has emerged as a prominent technique for LLM-generated content detection by embedding imperceptible patterns. Despite supreme performance, its robustness against adversarial attacks remains underexplored. Previous work…