Related papers: Removing Backdoor-Based Watermarks in Neural Netwo…

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…

Image watermarking is a technique for hiding information into images that can withstand distortions while requiring the encoded image to be perceptually identical to the original image. Recent work based on deep neural networks (DNN) has…

With the development of deep learning, high-value and high-cost models have become valuable assets, and related intellectual property protection technologies have become a hot topic. However, existing model watermarking work in black-box…

Superimposing visible watermarks on images provides a powerful weapon to cope with the copyright issue. Watermark removal techniques, which can strengthen the robustness of visible watermarks in an adversarial way, have attracted increasing…

The rapid advancement of deep learning has turned models into highly valuable assets due to their reliance on massive data and costly training processes. However, these models are increasingly vulnerable to leakage and theft, highlighting…

The rapid development of deep learning has benefited from the release of some high-quality open-sourced datasets ($e.g.$, ImageNet), which allows researchers to easily verify the effectiveness of their algorithms. Almost all existing…

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…

Deep Neural Networks have created a paradigm shift in our ability to comprehend raw data in various important fields ranging from computer vision and natural language processing to intelligence warfare and healthcare. While DNNs are…

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…

Instruction-driven image editing allows users to quickly edit an image according to text instructions in a forward pass. Nevertheless, malicious users can easily exploit this technique to create fake images, which could cause a crisis of…

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…

In the era of costly pre-training of large language models, ensuring the intellectual property rights of model owners, and insuring that said models are responsibly deployed, is becoming increasingly important. To this end, we propose model…

In recent trends, one can observe Large Language Models (LLMs) are exposed to backdoor attacks where vicious triggers added during training or model editing to elicit harmful outputs on specific input patterns while maintaining clean…

Machine learning (ML) models are applied in an increasing variety of domains. The availability of large amounts of data and computational resources encourages the development of ever more complex and valuable models. These models are…

To support various applications, a prevalent and efficient approach for business owners is leveraging their valuable datasets to fine-tune a pre-trained LLM through the API provided by LLM owners or cloud servers. However, this process…

Watermarking is an operation of embedding an information into an image in a way that allows to identify ownership of the image despite applying some distortions on it. In this paper, we presented a novel end-to-end solution for embedding…

Training machine learning (ML) models is expensive in terms of computational power, amounts of labeled data and human expertise. Thus, ML models constitute intellectual property (IP) and business value for their owners. Embedding digital…

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…

Federated graph learning (FedGL) is an emerging learning paradigm to collaboratively train graph data from various clients. However, during the development and deployment of FedGL models, they are susceptible to illegal copying and model…

Watermarking generative models consists of planting a statistical signal (watermark) in a model's output so that it can be later verified that the output was generated by the given model. A strong watermarking scheme satisfies the property…