Related papers: Efficient and Universal Watermarking for LLM-Gener…

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…

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…

The rapid advancement of customized Large Language Models (LLMs) offers considerable convenience. However, it also intensifies concerns regarding the protection of copyright/confidential information. With the extensive adoption of private…

With generative models producing high quality images that are indistinguishable from real ones, there is growing concern regarding the malicious usage of AI-generated images. Imperceptible image watermarking is one viable solution towards…

A recent and exciting thread of work focuses on developing methods for watermarking the output of large language models (LLMs). We focus on provably undetectable watermarking-that is, schemes that do not alter the output distribution of the…

Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal attacks, these methods…

The proliferation of AI-generated content brings significant concerns on the forensic and security issues such as source tracing, copyright protection, etc, highlighting the need for effective watermarking technologies. Font-based text…

Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data, raising the possibility that these models may have been trained on proprietary datasets or the same benchmarks used for evaluation. This…

The strong performance of large language models (LLMs) raises extensive discussion on their application to code generation. Recent research suggests continuous program refinements through visible tests to improve code generation accuracy in…

Integrating watermarks into generative images is a critical strategy for protecting intellectual property and enhancing artificial intelligence security. This paper proposes Plug-in Generative Watermarking (PiGW) as a general framework for…

In this paper, we initiate the study of \emph{multi-designated detector watermarking (MDDW)} for large language models (LLMs). This technique allows model providers to generate watermarked outputs from LLMs with two key properties: (i) only…

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…

Artificial Intelligence (AI) techniques, especially Large Language Models (LLMs), have started gaining popularity among researchers and software developers for generating source code. However, LLMs have been shown to generate code with…

Efficient knowledge injection methods for Large Language Models (LLMs), such as In-Context Learning, knowledge editing, and efficient parameter fine-tuning, significantly enhance model utility on downstream tasks. However, they also pose…

Generative images have proliferated on Web platforms in social media and online copyright distribution scenarios, and semantic watermarking has increasingly been integrated into diffusion models to support reliable provenance tracking and…

The widespread use of Large Language Models (LLMs) raises critical concerns regarding the unauthorized inclusion of copyrighted content in training data. Existing detection frameworks, such as DE-COP, are computationally intensive, and…

The rapid development of Large Language Models (LLMs) has intensified concerns about content traceability and potential misuse. Existing watermarking schemes for sampled text often face trade-offs between maintaining text quality and…

Generative code models (GCMs) significantly enhance development efficiency through automated code generation and code summarization. However, building and training these models require computational resources and time, necessitating…

Watermarking has recently emerged as an effective strategy for detecting the generations of large language models (LLMs). The strength of a watermark typically depends strongly on the entropy afforded by the language model and the set of…

We present SWaRL, a robust and fidelity-preserving watermarking framework designed to protect the intellectual property of code LLMs by embedding unique and verifiable signatures in the generated program. Existing watermarking approaches…