Related papers: How Good is Post-Hoc Watermarking With Language Mo…
The recent large-scale emergence of LLMs has left an open space for dealing with their consequences, such as plagiarism or the spread of false information on the Internet. Coupling this with the rise of AI detector bypassing tools, reliable…
The rapid development of LLMs has raised concerns about their potential misuse, leading to various watermarking schemes that typically offer high detectability. However, existing watermarking techniques often face trade-off between…
Watermarking combines an imperceptible change to an input image that will trigger a detector, to assert provenance and protect intellectual property. The literature has shown great interest in attacks on watermarking schemes: attackers are…
The indistinguishability of AI-generated content from human text raises challenges in transparency and accountability. While several methods exist to watermark models behind APIs, embedding watermark strategies directly into model weights…
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.…
In this paper, we study the problem of watermarking large language models (LLMs). We consider the trade-off between model distortion and detection ability and formulate it as a constrained optimization problem based on the red-green list…
Text watermarking algorithms for large language models (LLMs) can effectively identify machine-generated texts by embedding and detecting hidden features in the text. Although the current text watermarking algorithms perform well in most…
Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely…
Recent years have seen a surge in interest in digital content watermarking techniques, driven by the proliferation of generative models and increased legal pressure. With an ever-growing percentage of AI-generated content available online,…
Watermarking has recently emerged as an effective strategy for detecting the outputs of large language models (LLMs). Most existing schemes require white-box access to the model's next-token probability distribution, which is typically not…
In-generation watermarking for latent diffusion models has recently shown high robustness in marking generated images for easier detection and attribution. However, its application to autoregressive (AR) image models is underexplored.…
Large Language Models (LLMs) are increasingly fine-tuned on smaller, domain-specific datasets to improve downstream performance. These datasets often contain proprietary or copyrighted material, raising the need for reliable safeguards…
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…
Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and…
Watermarking of large language models (LLMs) generation embeds an imperceptible statistical pattern within texts, making it algorithmically detectable. Watermarking is a promising method for addressing potential harm and biases from LLMs,…
The rapid proliferation of generative audio synthesis and editing technologies has raised serious concerns about copyright infringement, data provenance, and the spread of misinformation via deepfake audio. Watermarking offers a proactive…
Text content created by humans or language models is often stolen or misused by adversaries. Tracing text provenance can help claim the ownership of text content or identify the malicious users who distribute misleading content like…
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…
Image generation algorithms are increasingly integral to diverse aspects of human society, driven by their practical applications. However, insufficient oversight in artificial Intelligence generated content (AIGC) can facilitate the spread…
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…