Related papers: DeepTracer: Tracing Stolen Model via Deep Coupled …

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…

Deep learning has been achieving top performance in many tasks. Since training of a deep learning model requires a great deal of cost, we need to treat neural network models as valuable intellectual properties. One concern in such a…

Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based solutions are easily compromised by distortions like codec…

Watermarking of language model outputs enables statistical detection of model-generated text, which can mitigate harms and misuses of language models. Existing watermarking strategies operate by altering the decoder of an existing language…

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…

This paper presents a traitor-tracing technique based on the watermarking of digital documents (\pdf{} files in particular). The watermarking algorithm uses a chain of three separate techniques that work in synergy. The embedded payload can…

Latent-based diffusion model watermarking embeds watermarks into generated images' latent space to enable content attribution, offering a training-free solution for intellectual property protection and digital forensics. However, these…

Federated learning (FL) is a distributed machine learning paradigm allowing multiple clients to collaboratively train a global model without sharing their local data. However, FL entails exposing the model to various participants. This…

Latent diffusion models have exhibited considerable potential in generative tasks. Watermarking is considered to be an alternative to safeguard the copyright of generative models and prevent their misuse. However, in the context of model…

Being trained on large and vast datasets, visual foundation models (VFMs) can be fine-tuned for diverse downstream tasks, achieving remarkable performance and efficiency in various computer vision applications. The high computation cost of…

With the widespread deployment of deep neural network (DNN) models, dynamic watermarking techniques are being used to protect the intellectual property of model owners. However, recent studies have shown that existing watermarking schemes…

In response to the growing popularity of Machine Learning (ML) techniques to solve problems in various industries, various malicious groups have started to target such techniques in their attack plan. However, as ML models are constantly…

Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models -- in principle, the watermark should be preserved when an…

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…

The current work is focusing on the implementation of a robust watermarking algorithm for digital images, which is based on an innovative spread spectrum analysis algorithm for watermark embedding and on a content-based image retrieval…

Self-supervised learning is an emerging machine learning paradigm. Compared to supervised learning which leverages high-quality labeled datasets, self-supervised learning relies on unlabeled datasets to pre-train powerful encoders which can…

The vast amounts of digital content captured from the real world or AI-generated media necessitate methods for copyright protection, traceability, or data provenance verification. Digital watermarking serves as a crucial approach to address…

Backdoor-based watermarking schemes were proposed to protect the intellectual property of artificial intelligence models, especially deep neural networks, under the black-box setting. Compared with ordinary backdoors, backdoor-based…

Federated Language Model (FedLM) allows a collaborative learning without sharing raw data, yet it introduces a critical vulnerability, as every untrustworthy client may leak the received functional model instance. Current watermarking…

Digital image watermarking is the process of embedding and extracting a watermark covertly on a cover-image. To dynamically adapt image watermarking algorithms, deep learning-based image watermarking schemes have attracted increased…