Related papers: Data Leakage in Visual Datasets

Data discovery from data lakes is an essential application in modern data science. While many previous studies focused on improving the efficiency and effectiveness of data discovery, little attention has been paid to the usability of such…

Identifying the causes of a model's unfairness is an important yet relatively unexplored task. We look into this problem through the lens of training data - the major source of unfairness. We ask the following questions: How would the…

Development of new machine learning models is typically done on manually curated data sets, making them unsuitable for evaluating the models' performance during operations, where the evaluation needs to be performed automatically on…

Today's success of state of the art methods for semantic segmentation is driven by large datasets. Data is considered an important asset that needs to be protected, as the collection and annotation of such datasets comes at significant…

Text-to-image synthesis has become highly popular for generating realistic and stylized images, often requiring fine-tuning generative models with domain-specific datasets for specialized tasks. However, these valuable datasets face risks…

With the growing popularity of artificial intelligence and machine learning, a wide spectrum of attacks against deep learning models have been proposed in the literature. Both the evasion attacks and the poisoning attacks attempt to utilize…

Malware, a persistent cybersecurity threat, increasingly targets interconnected digital systems such as desktop, mobile, and IoT platforms through sophisticated attack vectors. By exploiting these vulnerabilities, attackers compromise the…

The increasing complexity of large language models (LLMs) raises concerns about their ability to "cheat" on standard Question Answering (QA) benchmarks by memorizing task-specific data. This undermines the validity of benchmark evaluations,…

This paper focuses on investigation of confidential documents leaks in the form of screen photographs. Proposed approach does not try to prevent leak in the first place but rather aims to determine source of the leak. Method works by…

Modern software systems are developed in diverse programming languages and often harbor critical vulnerabilities that attackers can exploit to compromise security. These vulnerabilities have been actively targeted in real-world attacks,…

Machine learning (ML) approaches to data analysis are now widely adopted in many fields including epidemiology and medicine. To apply these approaches, confounds must first be removed as is commonly done by featurewise removal of their…

In machine learning, a bias occurs whenever training sets are not representative for the test data, which results in unreliable models. The most common biases in data are arguably class imbalance and covariate shift. In this work, we aim to…

In a biometric authentication or identification system, the matcher compares a stored and a fresh template to determine whether there is a match. This assessment is based on both a similarity score and a predefined threshold. For better…

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

We investigate the contents of web-scraped data for training AI systems, at sizes where human dataset curators and compilers no longer manually annotate every sample. Building off of prior privacy concerns in machine learning models, we…

Information theoretic leakage metrics quantify the amount of information about a private random variable $X$ that is leaked through a correlated revealed variable $Y$. They can be used to evaluate the privacy of a system in which an…

In this thesis we consider the problem of information hiding in the scenarios of interactive systems, statistical disclosure control, and refinement of specifications. We apply quantitative approaches to information flow in the first two…

Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 question-answer pairs, with privately held ground-truth…

With the recent growth in computer vision applications, the question of how fair and unbiased they are has yet to be explored. There is abundant evidence that the bias present in training data is reflected in the models, or even amplified.…

Time series data are prevalent across various domains and often encompass large datasets containing multiple time-dependent features in each sample. Exploring time-varying data is critical for data science practitioners aiming to understand…