Related papers: A Calibrated Memorization Index (MI) for Detecting…

Despite being trained on balanced datasets, existing AI-generated image detectors often exhibit systematic bias at test time, frequently misclassifying fake images as real. We hypothesize that this behavior stems from distributional shift…

Imitation learning considerably simplifies policy synthesis compared to alternative approaches by exploiting access to expert demonstrations. For such imitation policies, errors away from the training samples are particularly critical. Even…

Federated learning is a distributed learning technique that allows training a global model with the participation of different data owners without the need to share raw data. This architecture is orchestrated by a central server that…

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

The widespread use of diffusion models has led to an abundance of AI-generated data, raising concerns about model collapse -- a phenomenon in which recursive iterations of training on synthetic data lead to performance degradation. Prior…

Magnetic resonance (MR) imaging offers a wide variety of imaging techniques. A large amount of data is created per examination which needs to be checked for sufficient quality in order to derive a meaningful diagnosis. This is a manual…

Generating multi-contrasts/modal MRI of the same anatomy enriches diagnostic information but is limited in practice due to excessive data acquisition time. In this paper, we propose a novel deep-learning model for joint reconstruction and…

Mutual Information (MI) is a fundamental metric for quantifying dependency between two random variables. When we can access only the samples, but not the underlying distribution functions, we can evaluate MI using sample-based estimators.…

The CIFAR-10 and CIFAR-100 datasets are two of the most heavily benchmarked datasets in computer vision and are often used to evaluate novel methods and model architectures in the field of deep learning. However, we find that 3.3% and 10%…

Machine learning models that are overfitted/overtrained are more vulnerable to knowledge leakage, which poses a risk to privacy. Suppose we download or receive a model from a third-party collaborator without knowing its training accuracy.…

An important goal of self-supervised learning is to enable model pre-training to benefit from almost unlimited data. However, one method that has recently become popular, namely masked image modeling (MIM), is suspected to be unable to…

When do diffusion models reproduce their training data, and when are they able to generate samples beyond it? A practically relevant theoretical understanding of this interplay between memorization and generalization may significantly…

Synthetic cardiac MRI (CMRI) generation has emerged as a promising strategy to overcome the scarcity of annotated medical imaging data. Recent advances in GANs, VAEs, diffusion probabilistic models, and flow-matching techniques aim to…

Recent research has shown that representation learning models may accidentally memorize their training data. For example, the d\'ej\`a vu method shows that for certain representation learning models and training images, it is sometimes…

We propose MelodySim, a melody-aware music similarity model and dataset for plagiarism detection. First, we introduce a novel method to construct a dataset focused on melodic similarity. By augmenting Slakh2100, an existing MIDI dataset, we…

Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In…

Mislabeled data is a pervasive issue that undermines the performance of machine learning systems in real-world applications. An effective approach to mitigate this problem is to detect mislabeled instances and subject them to special…

Magnetic Resonance Imaging (MRI) diagnoses and manages a wide range of diseases, yet long scan times drive high costs and limit accessibility. AI methods have demonstrated substantial potential for reducing scan times, but despite rapid…

The problem of corrupted data, missing features, or missing modalities continues to plague the modern machine learning landscape. To address this issue, a class of regularization methods that enforce consistency between imputed and fully…

For many evaluation metrics commonly used as benchmarks for unconditional image generation, trivially memorizing the training set attains a better score than models which are considered state-of-the-art; we consider this problematic. We…