Related papers: A Resilient and Accessible Distribution-Preserving…
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…
Invisible watermarking of AI-generated images can help with copyright protection, enabling detection and identification of AI-generated media. In this work, we present a novel approach to watermark images of T2I Latent Diffusion Models…
Robust invisible watermarking schemes aim to embed hidden information into images such that the watermark survives common manipulations. However, powerful diffusion-based image generation and editing techniques now pose a new threat to…
Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design. To address this issue, we propose SemStamp, a robust sentence-level semantic watermarking algorithm based on locality-sensitive…
Diffusion models generate high-quality images but pose serious risks like copyright violation and disinformation. Watermarking is a key defense for tracing and authenticating AI-generated content. However, existing methods rely on…
Watermarking technology has gained significant attention due to the increasing importance of intellectual property (IP) rights, particularly with the growing deployment of large language models (LLMs) on billions resource-constrained edge…
Watermarking has emerged as a promising technique for detecting texts generated by LLMs. Current research has primarily focused on three design criteria: high quality of the watermarked text, high detectability, and robustness against…
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…
Diffusion models have gained prominence in the image domain for their capabilities in data generation and transformation, achieving state-of-the-art performance in various tasks in both image and audio domains. In the rapidly evolving field…
This paper introduces a novel watermarking method for diffusion models. It is based on guiding the diffusion process using the gradient computed from any off-the-shelf watermark decoder. The gradient computation encompasses different image…
Watermarking is broadly utilized to protect ownership of shared data while preserving data utility. However, existing watermarking methods for tabular datasets fall short on the desired properties (detectability, non-intrusiveness, and…
Large Language Models (LLMs) can be misused to spread unwanted content at scale. Content watermarking deters misuse by hiding messages in content, enabling its detection using a secret watermarking key. Robustness is a core security…
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,…
Deep neural network (DNN) watermarking is a suitable method for protecting the ownership of deep learning (DL) models. It secretly embeds an identifier (watermark) within the model, which can be retrieved by the owner to prove ownership. In…
Statistical watermarking is a common approach for verifying whether text was written by a language model. Most existing schemes assume autoregressive generation, where tokens are produced left to right and contextual hashing is well…
Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized…
Digital image watermarking is the process of embedding and extracting watermark covertly on a carrier image. Incorporating deep learning networks with image watermarking has attracted increasing attention during recent years. However,…
The rise of machine learning as a service and model sharing platforms has raised the need of traitor-tracing the models and proof of authorship. Watermarking technique is the main component of existing methods for protecting copyright of…
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…
Generative AI raises many societal concerns such as boosting disinformation and propaganda campaigns. Watermarking AI-generated content is a key technology to address these concerns and has been widely deployed in industry. However,…