相关论文: Data Leakage in Visual Datasets

Network theory and inverse modeling are two standard tools of applied physics, whose combination is needed when studying the dynamical organization of spatially distributed systems from indirect measurements. However, the associated…

Visual diffusion models have revolutionized the field of creative AI, producing high-quality and diverse content. However, they inevitably memorize training images or videos, subsequently replicating their concepts, content, or styles…

Query expansion methods powered by large language models (LLMs) have demonstrated effectiveness in zero-shot retrieval tasks. These methods assume that LLMs can generate hypothetical documents that, when incorporated into a query vector,…

We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model,…

Synthetic data generation is gaining increasing popularity in different computer vision applications. Existing state-of-the-art face recognition models are trained using large-scale face datasets, which are crawled from the Internet and…

Graphical perception studies typically measure visualization encoding effectiveness using the error of an "average observer", leading to canonical rankings of encodings for numerical attributes: e.g., position > area > angle > volume. Yet…

Detection and quantification of information leaks through timing side channels are important to guarantee confidentiality. Although static analysis remains the prevalent approach for detecting timing side channels, it is computationally…

We study the role of information complexity in privacy leakage about an attribute of an adversary's interest, which is not known a priori to the system designer. Considering the supervised representation learning setup and using neural…

Dataset Condensation is a newly emerging technique aiming at learning a tiny dataset that captures the rich information encoded in the original dataset. As the size of datasets contemporary machine learning models rely on becomes…

While federated learning (FL) promises to preserve privacy, recent works in the image and text domains have shown that training updates leak private client data. However, most high-stakes applications of FL (e.g., in healthcare and finance)…

Visual search is an essential part of almost any everyday human goal-directed interaction with the environment. Nowadays, several algorithms are able to predict gaze positions during simple observation, but few models attempt to simulate…

Visualizations help communicate data insights, but deceptive data representations can distort their interpretation and propagate misinformation. While recent Vision Language Models (VLMs) perform well on many chart understanding tasks,…

Recent studies have shown that distributed machine learning is vulnerable to gradient inversion attacks, where private training data can be reconstructed by analyzing the gradients of the models shared in training. Previous attacks…

Many statistical learning models hold an assumption that the training data and the future unlabeled data are drawn from the same distribution. However, this assumption is difficult to fulfill in real-world scenarios and creates barriers in…

Visual quality inspection in high performance manufacturing can benefit from automation, due to cost savings and improved rigor. Deep learning techniques are the current state of the art for generic computer vision tasks like classification…

Synthetic data generation is important to training and evaluating neural models for question answering over knowledge graphs. The quality of the data and the partitioning of the datasets into training, validation and test splits impact the…

Despite machine learning models being widely used today, the relationship between a model and its training dataset is not well understood. We explore correlation inference attacks, whether and when a model leaks information about the…

Side-channel attacks that leak sensitive information through a computing device's interaction with its physical environment have proven to be a severe threat to devices' security, particularly when adversaries have unfettered physical…

We provide the first systematic assessment of data leakage issues in the use of machine learning on panel data. Our organizing framework clarifies why neglecting the cross-sectional and longitudinal structure of these data leads to…

Data-driven decision making has been a common task in today's big data era, from simple choices such as finding a fast way to drive home, to complex decisions on medical treatment. It is often supported by visual analytics. For various…