相关论文: Provably Unlearnable Data Examples

In designed experiments and surveys, known laws or design feat ures provide checks on the most relevant aspects of a model and identify the target parameters. In contrast, in most observational studies in the health and social sciences, the…

Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do if they detect that some data was manipulated or incorrect.…

Federated Unlearning (FU) has emerged as a promising solution to respond to the right to be forgotten of clients, by allowing clients to erase their data from global models without compromising model performance. Unfortunately, researchers…

To steer language models towards truthful outputs on tasks which are beyond human capability, previous work has suggested training models on easy tasks to steer them on harder ones (easy-to-hard generalization), or using unsupervised…

Machine unlearning for large language models (LLMs) aims to remove undesired data, knowledge, and behaviors (e.g., for safety, privacy, or copyright) while preserving useful model capabilities. Despite rapid progress over the past two…

The widespread use of face recognition technology has given rise to privacy concerns, as many individuals are worried about the collection and utilization of their facial data. To address these concerns, researchers are actively exploring…

Unexploitable example generation aims to transform personal images into their unexploitable (unlearnable) versions before they are uploaded online, thereby preventing unauthorized exploitation of online personal images. Recently, this task…

Machine unlearning aims to remove points from the training dataset of a machine learning model after training: e.g., when a user requests their data to be deleted. While many unlearning methods have been proposed, none of them enable users…

The ability to replicate predictions by machine learning (ML) or artificial intelligence (AI) models and results in scientific workflows that incorporate such ML/AI predictions is driven by numerous factors. An uncertainty-aware metric that…

In this study, a novel idea, Uncertainty Structure Estimation (USE), a lightweight, algorithm-agnostic procedure that emphasizes the often-overlooked role of unlabeled data quality is introduced for Semi-supervised learning (SSL). SSL has…

Uncertainty quantification (UQ) is essential for assessing the reliability of Earth observation (EO) products. However, the extensive use of machine learning models in EO introduces an additional layer of complexity, as those models…

Motivation: Recent work has demonstrated the feasibility of using non-numerical, qualitative data to parameterize mathematical models. However, uncertainty quantification (UQ) of such parameterized models has remained challenging because of…

Private data, when published online, may be collected by unauthorized parties to train deep neural networks (DNNs). To protect privacy, defensive noises can be added to original samples to degrade their learnability by DNNs. Recently,…

During pretraining, LLMs inadvertently memorize sensitive or copyrighted data, posing significant compliance challenges under legal frameworks like the GDPR and the EU AI Act. Fulfilling these mandates demands techniques that can remove…

Recent work has improved recommendation models remarkably by equipping them with debiasing methods. Due to the unavailability of fully-exposed datasets, most existing approaches resort to randomly-exposed datasets as a proxy for evaluating…

Identifying and handling label errors can significantly enhance the accuracy of supervised machine learning models. Recent approaches for identifying label errors demonstrate that a low self-confidence of models with respect to a certain…

Existing similarity-based weakly supervised learning approaches often rely on precise similarity annotations between data pairs, which may inadvertently expose sensitive label information and raise privacy risks. To mitigate this issue, we…

Recent advancements in the capabilities of large language models (LLMs) have paved the way for a myriad of groundbreaking applications in various fields. However, a significant challenge arises as these models often "hallucinate", i.e.,…

Positive-unlabeled (PU) learning is a weakly supervised binary classification problem, in which the goal is to learn a binary classifier from only positive and unlabeled data, without access to negative data. In recent years, many PU…

Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged…