Related papers: A Survey of Fragile Model Watermarking

It is crucial to protect the intellectual property rights of DNN models prior to their deployment. The DNN should perform two main tasks: its primary task and watermarking task. This paper proposes a lightweight, reliable, and secure DNN…

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…

Many learning tasks require us to deal with graph data which contains rich relational information among elements, leading increasing graph neural network (GNN) models to be deployed in industrial products for improving the quality of…

Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has…

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…

With the increasing use of the internet and the ease of exchange of multimedia content, the protection of ownership rights has become a significant concern. Watermarking is an efficient means for this purpose. In many applications,…

Digital media is the need of a people now a day as the alternate of paper media.As the technology grown up digital media required protection while transferring through internet or others mediums.Watermarking techniques have been developed…

With the advancement of intelligent healthcare, medical pre-trained language models (Med-PLMs) have emerged and demonstrated significant effectiveness in downstream medical tasks. While these models are valuable assets, they are vulnerable…

Robust invisible watermarks are widely used to support copyright protection, content provenance, and accountability by embedding hidden signals designed to survive common post-processing operations. However, diffusion-based image editing…

The functionality of a deep learning (DL) model can be stolen via model extraction where an attacker obtains a surrogate model by utilizing the responses from a prediction API of the original model. In this work, we propose a novel…

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…

Generative image modeling enables a wide range of applications but raises ethical concerns about responsible deployment. This paper introduces an active strategy combining image watermarking and Latent Diffusion Models. The goal is for all…

Recent advancement in large-scale Artificial Intelligence (AI) models offering multimodal services have become foundational in AI systems, making them prime targets for model theft. Existing methods select Out-of-Distribution (OoD) data as…

Engineering a top-notch deep learning model is an expensive procedure that involves collecting data, hiring human resources with expertise in machine learning, and providing high computational resources. For that reason, deep learning…

We study a basic question about cryptographic watermarking for generative models: how reliable can a watermark remain when an adversary is allowed to corrupt the encoded signal? To address this question, we introduce a minimal coding…

We address the problem of watermarking graph objects, which consists in hiding information within them, to prove their origin. The two existing methods to watermark graphs use subgraph matching or graph isomorphism techniques, which are…

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…

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…

Federated learning is a distributed learning technique where machine learning models are trained on client devices in which the local training data resides. The training is coordinated via a central server which is, typically, controlled by…

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…