Related papers: Training Data Attribution: Was Your Model Secretly…

Embedding watermarks into the output of generative models is essential for establishing copyright and verifiable ownership over the generated content. Emerging diffusion model watermarking methods either embed watermarks in the frequency…

Text-to-image (T2I) models have recently gained widespread adoption. This has spurred concerns about safeguarding intellectual property rights and an increasing demand for mechanisms that prevent the generation of specific artistic styles.…

Artificial intelligence models trained from data can only be as good as the underlying data is. Biases in training data propagating through to the output of a machine learning model are a well-documented and well-understood phenomenon, but…

Recent work has demonstrated the successful extraction of training data from generative language models. However, it is not evident whether such extraction is feasible in text classification models since the training objective is to predict…

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…

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…

Watermarking is a technique that involves embedding nearly unnoticeable statistical signals within generated content to help trace its source. This work focuses on a scenario where an untrusted third-party user sends prompts to a trusted…

Text-to-image generation models have recently attracted unprecedented attention as they unlatch imaginative applications in all areas of life. However, developing such models requires huge amounts of data that might contain…

Text-to-image synthesis has become highly popular for generating realistic and stylized images, often requiring fine-tuning generative models with domain-specific datasets for specialized tasks. However, these valuable datasets face risks…

LLM watermarks stand out as a promising way to attribute ownership of LLM-generated text. One threat to watermark credibility comes from spoofing attacks, where an unauthorized third party forges the watermark, enabling it to falsely…

The proliferation of diffusion models trained on web-scale, provenance-uncertain image collections has made it essential, yet technically unresolved, to determine whether a model has learned from specific copyrighted data without…

With the growing adoption of data privacy regulations, the ability to erase private or copyrighted information from trained models has become a crucial requirement. Traditional unlearning methods often assume access to the complete training…

Data attribution methods, which quantify the influence of individual training data points on a machine learning model, have gained increasing popularity in data-centric applications in modern AI. Despite a recent surge of new methods…

Generative models have seen an explosion in popularity with the release of huge generative Diffusion models like Midjourney and Stable Diffusion to the public. Because of this new ease of access, questions surrounding the automated…

Copyright law confers upon creators the exclusive rights to reproduce, distribute, and monetize their creative works. However, recent progress in text-to-image generation has introduced formidable challenges to copyright enforcement. These…

This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed the most to the…

We study protecting a user's data (images in this work) against a learner's unauthorized use in training neural networks. It is especially challenging when the user's data is only a tiny percentage of the learner's complete training set. We…

The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a…

High-fidelity text-to-image diffusion models have revolutionized visual content generation, but their widespread use raises significant ethical concerns, including intellectual property protection and the misuse of synthetic media. To…

The goal of data attribution is to trace the model's predictions through the learning algorithm and back to its training data. thereby identifying the most influential training samples and understanding how the model's behavior leads to…