相关论文: SWAN: Semantic Watermarking with Abstract Meaning …

Semantic-level watermarking (SWM) for large language models (LLMs) enhances watermarking robustness against text modifications and paraphrasing attacks by treating the sentence as the fundamental unit. However, existing methods still lack…

Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to paragraph-level paraphrasing remains difficult because such attacks globally disrupt watermark…

Speech watermarking techniques can proactively mitigate the potential harmful consequences of instant voice cloning techniques. These techniques involve the insertion of signals into speech that are imperceptible to humans but can be…

Generative models have rapidly evolved to generate realistic outputs. However, their synthetic outputs increasingly challenge the clear distinction between natural and AI-generated content, necessitating robust watermarking techniques.…

LLM watermarks must be detectable without compromising text quality, yet most existing schemes bias the next-token distribution and pay for detection with measurable quality loss. We present SLAM (Structural Linguistic Activation Marking),…

This paper proposes a novel approach towards image authentication and tampering detection by using watermarking as a communication channel for semantic information. We modify the HiDDeN deep-learning watermarking architecture to embed and…

Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. However, existing watermarking methods are often vulnerable to semantic-invariant attacks, such as…

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…

We develop a novel technique to parse English sentences into Abstract Meaning Representation (AMR) using SEARN, a Learning to Search approach, by modeling the concept and the relation learning in a unified framework. We evaluate our parser…

Safeguarding intellectual property and preventing potential misuse of AI-generated images are of paramount importance. This paper introduces a robust and agile plug-and-play watermark detection framework, dubbed as RAW. As a departure from…

Large language models (LLMs) have show great ability in various natural language tasks. However, there are concerns that LLMs are possible to be used improperly or even illegally. To prevent the malicious usage of LLMs, detecting…

Semantic watermarking techniques for latent diffusion models (LDMs) are robust against regeneration attacks, but often suffer from detection performance degradation due to the loss of frequency integrity. To tackle this problem, we propose…

Recent advances in digital watermarking make use of deep neural networks for message embedding and extraction. They typically follow the ``encoder-noise layer-decoder''-based architecture. By deliberately establishing a differentiable noise…

Benefiting from the superior capabilities of large language models in natural language understanding and generation, Embeddings-as-a-Service (EaaS) has emerged as a successful commercial paradigm on the web platform. However, prior studies…

The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLMs' outputs traceable without requiring…

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…

We introduce a new method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR). Compared with the original textual input, AMR is a structured semantic representation that presents the core concepts…

The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a promising solution: model owners can embed an imperceptible…

Multi-bit watermarking (MW) has been designed to enhance resistance against watermarking attacks, such as signal processing operations and geometric distortions. Various benchmark tools exist to assess this robustness through simulated…

Large language models generate high-quality responses with potential misinformation, underscoring the need for regulation by distinguishing AI-generated and human-written texts. Watermarking is pivotal in this context, which involves…