Related papers: EMA: Auditing Data Removal from Trained Models

With the increasing prevalence of Web-based platforms handling vast amounts of user data, machine unlearning has emerged as a crucial mechanism to uphold users' right to be forgotten, enabling individuals to request the removal of their…

Classical tests of fit typically reject a model for large enough real data samples. In contrast, often in statistical practice a model offers a good description of the data even though it is not the "true" random generator. We consider a…

Industrial and scientific applications handle large volumes of data that render manual validation by humans infeasible. Therefore, we require automated data validation approaches that are able to consider the prior knowledge of domain…

In the face of global economic uncertainty, financial auditing has become essential for regulatory compliance and risk mitigation. Traditional manual auditing methods are increasingly limited by large data volumes, complex business…

The Expectation Maximization (EM) algorithm is a versatile tool for model parameter estimation in latent data models. When processing large data sets or data stream however, EM becomes intractable since it requires the whole data set to be…

To use machine learning in high stakes applications (e.g. medicine), we need tools for building confidence in the system and evaluating whether it is reliable. Methods to improve model reliability often require new learning algorithms (e.g.…

Multivariate bounded discrete data arises in many fields. In the setting of dementia studies, such data is collected when individuals complete neuropsychological tests. We outline a modeling and inference procedure that can model the joint…

Ecological momentary assessment (EMA) data have a broad base of application in the study of time trends and relations. In EMA studies, there are a number of design considerations which influence the analysis of the data. One general…

Recent work shows membership inference attacks (MIAs) on large language models (LLMs) produce inconclusive results, partly due to difficulties in creating non-member datasets without temporal shifts. While researchers have turned to…

We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion requests, one often-cited potential application for unlearning…

Revoking personal private data is one of the basic human rights, which has already been sheltered by several privacy-preserving laws in many countries. However, with the development of data science, machine learning and deep learning…

Modern privacy regulations grant citizens the right to be forgotten by products, services and companies. In case of machine learning (ML) applications, this necessitates deletion of data not only from storage archives but also from ML…

Data contamination has become prevalent and challenging with the rise of models pretrained on large automatically-crawled corpora. For closed models, the training data becomes a trade secret, and even for open models, it is not trivial to…

Growing concerns over data privacy and security highlight the importance of machine unlearning--removing specific data influences from trained models without full retraining. Techniques like Membership Inference Attacks (MIAs) are widely…

The current trend in data regulation requirements and privacy-preserving machine learning has emphasized the importance of machine unlearning. The naive approach to unlearning training data by retraining over the complement of the forget…

Recent advances in machine learning have significantly impacted the field of information extraction, with Language Models (LMs) playing a pivotal role in extracting structured information from unstructured text. Prior works typically…

Machine learning (ML) models deployed in healthcare systems must face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, splitting datasets…

Gene Set Enrichment Analysis (GSEA) is a basic tool for genomic data treatment. From a statistical point of view, the centering of its test statistic does not allow the derivation of asymptotic results. A test statistic with a different…

Entity alignment (EA) aims at building a unified Knowledge Graph (KG) of rich content by linking the equivalent entities from various KGs. GNN-based EA methods present promising performances by modeling the KG structure defined by relation…

Machine learning models are vulnerable to adversarial attacks, including attacks that leak information about the model's training data. There has recently been an increase in interest about how to best address privacy concerns, especially…