Related papers: Unifying Watermarking via Dimension-Aware Mapping
A novel video watermarking system operating in the three dimensional wavelet transform is here presented. Specifically the video sequence is partitioned into spatio temporal units and the single shots are projected onto the 3D wavelet…
As large language models (LLMs) become integral to applications such as question answering and content creation, reliable content attribution has become increasingly important. Watermarking is a promising approach, but most existing methods…
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…
Methods for watermarking large language models have been proposed that distinguish AI-generated text from human-generated text by slightly altering the model output distribution, but they also distort the quality of the text, exposing the…
How do the neural networks distinguish two images? It is of critical importance to understand the matching mechanism of deep models for developing reliable intelligent systems for many risky visual applications such as surveillance and…
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…
Digital watermarking has been widely studied for the protection of intellectual property. Traditional watermarking schemes often design in a "wider" rule, which applies one general embedding mechanism to all images. But this will limit the…
Current image watermarking technologies are predominantly categorized into text watermarking techniques and image steganography; however, few methods can simultaneously handle text and image-based watermark data, which limits their…
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)…
The intellectual property (IP) of Deep neural networks (DNNs) can be easily ``stolen'' by surrogate model attack. There has been significant progress in solutions to protect the IP of DNN models in classification tasks. However, little…
Curating high quality datasets that play a key role in the emergence of new AI applications requires considerable time, money, and computational resources. So, effective ownership protection of datasets is becoming critical. Recently, to…
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…
Image watermarking techniques have continuously evolved to address new challenges and incorporate advanced features. The advent of data-driven approaches has enabled the processing and analysis of large volumes of data, extracting valuable…
In order to protect the intellectual property (IP) of deep neural networks (DNNs), many existing DNN watermarking techniques either embed watermarks directly into the DNN parameters or insert backdoor watermarks by fine-tuning the DNN…
We present a robust neural watermarking framework for scientific data integrity, targeting high-dimensional fields common in climate modeling and fluid simulations. Using a convolutional autoencoder, binary messages are invisibly embedded…
Large language models (LLMs) have demonstrated outstanding performance, making them valuable digital assets with significant commercial potential. Unfortunately, the LLM and its API are susceptible to intellectual property theft.…
The interactions between parameters, model structure, and outputs can determine what inferences, predictions, and control strategies are possible for a given system. Parameter space reduction and parameter estimation---and, more generally,…
Watermarking (WM) is a critical mechanism for detecting and attributing AI-generated content. Current WM methods for Large Language Models (LLMs) are predominantly tailored for autoregressive (AR) models: They rely on tokens being generated…
A new local watermarking method based on histogram shifting has been proposed in this paper to deal with various signal processing attacks (e.g. median filtering, JPEG compression and Gaussian noise addition) and geometric attacks (e.g.…
With LLM watermarking already being deployed commercially, practical applications increasingly require multibit watermarks that encode more complex payloads, such as user IDs or timestamps, into the generated text. In this work, we propose…