Related papers: Blameless Users in a Clean Room: Defining Copyrigh…

Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…

Users have the right to have their data deleted by third-party learned systems, as codified by recent legislation such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA). Such data deletion can…

We present Copyright Detective, the first interactive forensic system for detecting, analyzing, and visualizing potential copyright risks in LLM outputs. The system treats copyright infringement versus compliance as an evidence discovery…

As generative models become ubiquitous, there is a critical need for fine-grained control over the generation process. Yet, while controlled generation methods from prompting to fine-tuning proliferate, a fundamental question remains…

Personalized AI applications such as DreamBooth enable the generation of customized content from user images, but also raise significant privacy concerns, particularly the risk of facial identity leakage. Recent defense mechanisms like…

Large Language Models (LLMs) have transformed machine learning but raised significant legal concerns due to their potential to produce text that infringes on copyrights, resulting in several high-profile lawsuits. The legal landscape is…

Recent advances in diffusion models have significantly enhanced their ability to generate high-quality images and videos, but they have also increased the risk of producing unsafe content. Existing unlearning/editing-based methods for safe…

Generative audio models, based on diffusion and autoregressive architectures, have advanced rapidly in both quality and expressiveness. This progress, however, raises pressing copyright concerns, as such models are often trained on vast…

Exploring the data sources used to train Large Language Models (LLMs) is a crucial direction in investigating potential copyright infringement by these models. While this approach can identify the possible use of copyrighted materials in…

More and more companies' Intellectual Property (IP) is being integrated into Neural Network (NN) models. This IP has considerable value for companies and, therefore, requires adequate protection. For example, an attacker might replicate a…

With the rapid development of generative technology, current generative models can generate high-fidelity digital content and edit it in a controlled manner. However, there is a risk that malicious individuals might misuse these…

The rapid advancement of open-source foundation models has brought transparency and accessibility to this groundbreaking technology. However, this openness has also enabled the development of highly-capable, unsafe models, as exemplified by…

"Does generative AI infringe copyright?" is an urgent question. It is also a difficult question, for two reasons. First, "generative AI" is not just one product from one company. It is a catch-all name for a massive ecosystem of loosely…

Machine learning models are increasingly used in societal applications, yet legal and privacy concerns demand that they very often be kept confidential. Consequently, there is a growing distrust about the fairness properties of these models…

Artificial Intelligence (AI), and in particular generative models, are transformative tools for knowledge work. They problematise notions of creativity, originality, plagiarism, the attribution of credit, and copyright ownership. Critics of…

In recent decades, Generative Adversarial Network (GAN) and its variants have achieved unprecedented success in image synthesis. However, well-trained GANs are under the threat of illegal steal or leakage. The prior studies on remote…

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target…

Authorship Verification (AV) (do two documents have the same author?) is essential in many real-life applications. AV is often used in privacy-sensitive domains that require an offline proprietary model that is deployed on premises, making…

The success of deep learning is partly attributed to the availability of massive data downloaded freely from the Internet. However, it also means that users' private data may be collected by commercial organizations without consent and used…

Model stealing poses a significant security risk in machine learning by enabling attackers to replicate a black-box model without access to its training data, thus jeopardizing intellectual property and exposing sensitive information.…