相关论文: Set-Membership Inference Attacks using Data Waterm…

The recent progress in generative models has revolutionized the synthesis of highly realistic images, including face images. This technological development has undoubtedly helped face recognition, such as training data augmentation for…

Given how large parts of publicly available text are crawled to pretrain large language models (LLMs), data creators increasingly worry about the inclusion of their proprietary data for model training without attribution or licensing. Their…

Tabular data typically contains private and important information; thus, precautions must be taken before they are shared with others. Although several methods (e.g., differential privacy and k-anonymity) have been proposed to prevent…

In practical application, the widespread deployment of diffusion models often necessitates substantial investment in training. As diffusion models find increasingly diverse applications, concerns about potential misuse highlight the…

The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained…

Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference can be formalized as a hypothesis testing problem. The most…

Member inference (MI) attacks aim to determine if a specific data sample was used to train a machine learning model. Thus, MI is a major privacy threat to models trained on private sensitive data, such as medical records. In MI attacks one…

In recent years, various watermarking methods were suggested to detect computer vision models obtained illegitimately from their owners, however they fail to demonstrate satisfactory robustness against model extraction attacks. In this…

The widespread open-sourcing of advanced recommendation algorithms and the rising threat of model extraction attacks have made safeguarding the intellectual property of recommender systems an imperative task. While watermarking serves as a…

Watermarking is broadly utilized to protect ownership of shared data while preserving data utility. However, existing watermarking methods for tabular datasets fall short on the desired properties (detectability, non-intrusiveness, and…

Image generative models have become increasingly popular, but training them requires large datasets that are costly to collect and curate. To circumvent these costs, some parties may exploit existing models by using the generated images as…

The proliferation of generative image models has revolutionized AIGC creation while amplifying concerns over content provenance and manipulation forensics. Existing methods are typically either unable to localize tampering or restricted to…

Membership Inference Attacks have emerged as a dominant method for empirically measuring privacy leakage from machine learning models. Here, privacy is measured by the {\em{advantage}} or gap between a score or a function computed on the…

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…

The rapid proliferation of AI-generated images necessitates effective watermarking techniques to protect intellectual property and detect fraudulent content. While existing training-based watermarking methods show promise, they often…

We consider the problem of a training data proof, where a data creator or owner wants to demonstrate to a third party that some machine learning model was trained on their data. Training data proofs play a key role in recent lawsuits…

Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models. However, existing methods largely ignore the reprogramming property of deep models and thus may not fully…

Generative AI (GenAI) is transforming creative workflows through the capability to synthesize and manipulate images via high-level prompts. Yet creatives are not well supported to receive recognition or reward for the use of their content…

Large text-to-image models have shown remarkable performance in synthesizing high-quality images. In particular, the subject-driven model makes it possible to personalize the image synthesis for a specific subject, e.g., a human face or an…

Deep neural networks have recently achieved significant progress. Sharing trained models of these deep neural networks is very important in the rapid progress of researching or developing deep neural network systems. At the same time, it is…