Related papers: Provable Training Data Identification for Large La…

Detecting pre-training data in Large Language Models (LLMs) is crucial for auditing data privacy and copyright compliance, yet it remains challenging in black-box, zero-shot settings where computational resources and training data are…

Person re-identification (Re-ID) has achieved great improvement with deep learning and a large amount of labelled training data. However, it remains a challenging task for adapting a model trained in a source domain of labelled data to a…

This paper presents a new approach to identifying and eliminating mislabeled training instances for supervised learning. The goal of this approach is to improve classification accuracies produced by learning algorithms by improving the…

In this research we propose a new method for training predictive machine learning models for prescriptive applications. This approach, which we refer to as coupled validation, is based on tweaking the validation step in the standard…

Differential privacy provides a rigorous framework for privacy-preserving data analysis. This paper proposes the first differentially private procedure for controlling the false discovery rate (FDR) in multiple hypothesis testing. Inspired…

In this evolving era of machine learning security, membership inference attacks have emerged as a potent threat to the confidentiality of sensitive data. In this attack, adversaries aim to determine whether a particular point was used…

Obtaining high-quality data for collaborative training of machine learning models can be a challenging task due to A) regulatory concerns and B) a lack of data owner incentives to participate. The first issue can be addressed through the…

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…

Real-world data is often ambiguous; for example, human annotation produces instances with multiple conflicting class labels. Partial-label learning (PLL) aims at training a classifier in this challenging setting, where each instance is…

Pre-training data detection for LLMs is essential for addressing copyright concerns and mitigating benchmark contamination. Existing methods mainly focus on the likelihood-based statistical features or heuristic signals before and after…

Generalised Bayesian Inference (GBI) attempts to address model misspecification in a standard Bayesian setup by tempering the likelihood. The likelihood is raised to a fractional power, called the learning rate, which reduces its importance…

Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…

Benchmark data contamination has become a central challenge in LLM evaluation: when evaluation examples appear in the training data of one or more audited models, reported performance can be inflated and cross-model comparisons become…

Personalized Intelligence (PI) is the problem of providing customized AI experiences tailored to each individual user. In many applications, PI is preferred or even required. Existing personalization approaches involve fine-tuning…

Deep learning models achieve high predictive accuracy across a broad spectrum of tasks, but rigorously quantifying their predictive uncertainty remains challenging. Usable estimates of predictive uncertainty should (1) cover the true…

Non-destructive 3D imaging of large multi-particulate samples is essential for quantifying particle-level properties, such as size, shape, and spatial distribution, across applications in mining, materials science, and geology. However,…

In the field of machine learning, domain-specific annotated data is an invaluable resource for training effective models. However, in the medical domain, this data often includes Personal Health Information (PHI), raising significant…

This paper presents a framework for privacy-preserving verification of machine learning models, focusing on models trained on sensitive data. Integrating Local Differential Privacy (LDP) with model explanations from LIME and SHAP, our…

Pretrained large language models (LLMs) are able to solve a wide variety of tasks through transfer learning. Various explainability methods have been developed to investigate their decision making process. TracIn (Pruthi et al., 2020) is…

Controlling the false discovery rate (FDR) is a critical challenge in large-scale data analysis, particularly in the presence of outliers. A common practice involves imposing a Student-$t$ distribution to eliminate the influence of…