相关论文: Inoculation by Fine-Tuning: A Method for Analyzing…

Graph Neural Networks (GNNs) have achieved remarkable performance through their message-passing mechanism. However, recent studies have highlighted the vulnerability of GNNs to backdoor attacks, which can lead the model to misclassify…

Large Language Models (LLMs) are often trained with safety guards intended to prevent harmful text generation. However, such safety training can be removed by fine-tuning the LLM on harmful datasets. While this emerging threat (harmful…

The release of large natural language inference (NLI) datasets like SNLI and MNLI have led to rapid development and improvement of completely neural systems for the task. Most recently, heavily pre-trained, Transformer-based models like…

Data poisoning attacks compromise the integrity of machine-learning models by introducing malicious training samples to influence the results during test time. In this work, we investigate backdoor data poisoning attack on deep neural…

Current deep learning paradigms largely benefit from the tremendous amount of annotated data. However, the quality of the annotations often varies among labelers. Multi-observer studies have been conducted to study these annotation…

Traditional instance-based model analysis focuses mainly on misclassified instances. However, this approach overlooks the varying difficulty associated with different instances. Ideally, a robust model should recognize and reflect the…

Understanding and identifying different types of single molecules' diffusion that occur in a broad range of systems (including living matter) is extremely important, as it can provide information on the physical and chemical characteristics…

Motivated by the goals of dataset pruning and defect identification, a growing body of methods have been developed to score individual examples within a dataset. These methods, which we call "example difficulty scores", are typically used…

The presence of noisy labels in a training dataset can significantly impact the performance of machine learning models. To tackle this issue, researchers have explored methods for Learning with Noisy Labels to identify clean samples and…

In computational pathology, several foundation models have recently emerged and demonstrated enhanced learning capability for analyzing pathology images. However, adapting these models to various downstream tasks remains challenging,…

Adaptive medical AI models often face performance drops in dynamic clinical environments due to data drift. We propose an autonomous continuous monitoring and data integration framework that maintains robust performance over time. Focusing…

Fine-tuning pretrained contextual word embedding models to supervised downstream tasks has become commonplace in natural language processing. This process, however, is often brittle: even with the same hyperparameter values, distinct random…

Modern machine learning models are prone to over-reliance on spurious correlations, which can often lead to poor performance on minority groups. In this paper, we identify surprising and nuanced behavior of finetuned models on worst-group…

The aim of dataset distillation is to encode the rich features of an original dataset into a tiny dataset. It is a promising approach to accelerate neural network training and related studies. Different approaches have been proposed to…

Much machine learning research progress is based on developing models and evaluating them on a benchmark dataset (e.g., ImageNet for images). However, applying such benchmark-successful methods to real-world data often does not work as…

Indiscriminate data poisoning attacks aim to decrease a model's test accuracy by injecting a small amount of corrupted training data. Despite significant interest, existing attacks remain relatively ineffective against modern machine…

Recent progress in generative AI, primarily through diffusion models, presents significant challenges for real-world deepfake detection. The increased realism in image details, diverse content, and widespread accessibility to the general…

Deep convolutional neural networks (CNNs) for image denoising are usually trained on large datasets. These models achieve the current state of the art, but they have difficulties generalizing when applied to data that deviate from the…

This paper proposes a scenario-based functional testing approach for enhancing the performance of machine learning (ML) applications. The proposed method is an iterative process that starts with testing the ML model on various scenarios to…

We present GIFT: a {G}radient-aware {I}mmunization technique to defend diffusion models against malicious {F}ine-{T}uning while preserving their ability to generate safe content. Existing safety mechanisms like safety checkers are easily…