Related papers: When There Is No Decoder: Removing Watermarks from…
Copyright protection for deep neural networks (DNNs) is an urgent need for AI corporations. To trace illegally distributed model copies, DNN watermarking is an emerging technique for embedding and verifying secret identity messages in the…
The state of the art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements. Recently, [35, 22] proposed to watermark convolutional…
In recent years, there has been significant advancement in the field of model watermarking techniques. However, the protection of image-processing neural networks remains a challenge, with only a limited number of methods being developed.…
Motivated by the problem of detecting AI-generated text, we consider the problem of watermarking the output of language models with provable guarantees. We aim for watermarks which satisfy: (a) undetectability, a cryptographic notion…
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 been widely adopted for protecting the intellectual property (IP) of Deep Neural Networks (DNN) to defend the unauthorized distribution. Unfortunately, the popular data-poisoning DNN watermarking scheme relies on target…
We propose a novel multi-bit box-free watermarking method for the protection of Intellectual Property Rights (IPR) of GANs with improved robustness against white-box attacks like fine-tuning, pruning, quantization, and surrogate model…
Reports regarding the misuse of Generative AI (GenAI) to create deepfakes are frequent. Defensive watermarking enables GenAI providers to hide fingerprints in their images and use them later for deepfake detection. Yet, its potential has…
The rapid growth of transformer-based models increases the concerns about their integrity and ownership insurance. Watermarking addresses this issue by embedding a unique identifier into the model, while preserving its performance. However,…
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 policy catches up with the capabilities of generative AI, watermarking is central to content provenance efforts. Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization…
As diffusion models (DMs) enable photorealistic image generation at unprecedented scale, watermarking techniques have become essential for provenance establishment and accountability. Existing methods face challenges: sampling-based…
Trigger set-based watermarking schemes have gained emerging attention as they provide a means to prove ownership for deep neural network model owners. In this paper, we argue that state-of-the-art trigger set-based watermarking algorithms…
In this work, we introduce a novel deep learning-based approach to text-in-image watermarking, a method that embeds and extracts textual information within images to enhance data security and integrity. Leveraging the capabilities of deep…
The goal of 3D mesh watermarking is to embed the message in 3D meshes that can withstand various attacks imperceptibly and reconstruct the message accurately from watermarked meshes. The watermarking algorithm is supposed to withstand…
Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing watermarks are easily removed when facing model stealing…
Digital watermarking techniques are crucial for copyright protection and source identification of images, especially in the era of generative AI models. However, many existing watermarking methods, particularly content-agnostic approaches…
Invisible watermarking for autoregressive (AR) image generation has recently gained attention as a means of protecting image ownership and tracing AI-generated content. However, existing approaches suffer from three key limitations: (1)…
Watermarks for AI-generated images are meant to support downstream decisions about provenance, manipulation, and trust. In the settings that motivate watermark removal, therefore, success means more than causing the watermark test to fail.…
Recently, diffusion models (DMs) have become the state-of-the-art method for image synthesis. Editing models based on DMs, known for their high fidelity and precision, have inadvertently introduced new challenges related to image copyright…