Related papers: Dynamics-Level Watermarking of Flow Matching Model…

Generative models have rapidly evolved to generate realistic outputs. However, their synthetic outputs increasingly challenge the clear distinction between natural and AI-generated content, necessitating robust watermarking techniques.…

Deep learning techniques are one of the most significant elements of any Artificial Intelligence (AI) services. Recently, these Machine Learning (ML) methods, such as Deep Neural Networks (DNNs), presented exceptional achievement in…

Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data…

The widespread deployment of high-fidelity generative models has intensified the need for reliable mechanisms for provenance and content authentication. In-processing watermarking, embedding a signature into the generative model's synthesis…

Flow watermarks efficiently link packet flows in a network in order to thwart various attacks such as stepping stones. We study the problem of designing good flow watermarks. Earlier flow watermarking schemes mostly considered substitution…

Generative code models (GCMs) significantly enhance development efficiency through automated code generation and code summarization. However, building and training these models require computational resources and time, necessitating…

This paper introduces a novel watermarking method for diffusion models. It is based on guiding the diffusion process using the gradient computed from any off-the-shelf watermark decoder. The gradient computation encompasses different image…

Although deep neural networks have made tremendous progress in the area of multimedia representation, training neural models requires a large amount of data and time. It is well-known that utilizing trained models as initial weights often…

Data has been regarded as a valuable asset with the fast development of artificial intelligence technologies. In this paper, we introduce deep-learning neural network-based frequency-domain watermarking for protecting energy system time…

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…

This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike traditional information embedding, which embeds information…

In federated learning (FL), $K$ clients jointly train a model without sharing raw data. Because each participant invests data and compute, clients need mechanisms to later prove the provenance of a jointly trained model. Model watermarking…

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…

Industry 4.0's highly networked Machine Tool Controllers (MTCs) are prime targets for replay attacks that use outdated sensor data to manipulate actuators. Dynamic watermarking can reveal such tampering, but current schemes assume…

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…

Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows governed by ordinary differential equations. Despite growing…

As deep learning (DL) models are widely and effectively used in Machine Learning as a Service (MLaaS) platforms, there is a rapidly growing interest in DL watermarking techniques that can be used to confirm the ownership of a particular…

The advancement of Large Language Models (LLMs) has led to increasing concerns about the misuse of AI-generated text, and watermarking for LLM-generated text has emerged as a potential solution. However, it is challenging to generate…

In-generation watermarking for latent diffusion models has recently shown high robustness in marking generated images for easier detection and attribution. However, its application to autoregressive (AR) image models is underexplored.…

This paper presents a novel approach to deter unauthorized deepfakes and enable user tracking in generative models, even when the user has full access to the model parameters, by integrating key-based model authentication with watermarking…