Related papers: Membership and Dataset Inference Attacks on Large …

Membership inference attacks (MIAs) pose a critical threat to the privacy of training data in deep learning. Despite significant progress in attack methodologies, our understanding of when and how models encode membership information during…

We demonstrate how a target model's generalization gap leads directly to an effective deterministic black box membership inference attack (MIA). This provides an upper bound on how secure a model can be to MIA based on a simple metric.…

The increasing use of diffusion models for image generation, especially in sensitive areas like medical imaging, has raised significant privacy concerns. Membership Inference Attack (MIA) has emerged as a potential approach to determine if…

Large Language Models (LLMs) utilize large amounts of data for their training, some of which may come from copyrighted sources. Membership Inference Attacks (MIA) aim to detect those documents and whether they have been included in the…

Previous studies have developed fairness methods for biased models that exhibit discriminatory behaviors towards specific subgroups. While these models have shown promise in achieving fair predictions, recent research has identified their…

Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis. While both can be trained under differential privacy (DP) to protect sensitive data, their sensitivity to…

Diffusion Language Models (DLMs) represent a promising alternative to autoregressive language models, using bidirectional masked token prediction. Yet their susceptibility to privacy leakage via Membership Inference Attacks (MIA) remains…

Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point \textit{exactly} matches a…

Deep learning has achieved overwhelming success, spanning from discriminative models to generative models. In particular, deep generative models have facilitated a new level of performance in a myriad of areas, ranging from media…

The raise of machine learning and deep learning led to significant improvement in several domains. This change is supported by both the dramatic rise in computation power and the collection of large datasets. Such massive datasets often…

Analyzing time-series data that contains personal information, particularly in the medical field, presents serious privacy concerns. Sensitive health data from patients is often used to train machine learning models for diagnostics and…

Federated learning (FL) is a popular approach to facilitate privacy-aware machine learning since it allows multiple clients to collaboratively train a global model without granting others access to their private data. It is, however, known…

Membership inference attacks (MIAs) aim to determine whether a data sample was included in a machine learning (ML) model's training set and have become the de facto standard for measuring privacy leakages in ML. We propose an evaluation…

This study investigates the privacy risks associated with diffusion-based synthetic tabular data generation methods, focusing on their susceptibility to Membership Inference Attacks (MIAs). We examine two recent models, TabDDPM and TabSyn,…

OpenLVLM-MIA is a new benchmark that highlights fundamental challenges in evaluating membership inference attacks (MIA) against large vision-language models (LVLMs). While prior work has reported high attack success rates, our analysis…

Synthetic data generation plays an important role in enabling data sharing, particularly in sensitive domains like healthcare and finance. Recent advances in diffusion models have made it possible to generate realistic, high-quality tabular…

Tabular data sharing under privacy constraints is increasingly important for research and collaboration. Synthetic data generators (SDGs) are a promising solution, but synthetic data remains vulnerable to attacks, such as membership…

Federated Learning (FL) enables collaborative model training while keeping training data localized, allowing us to preserve privacy in various domains including remote sensing. However, recent studies show that FL models may still leak…

Recent studies have shown that deep learning models are vulnerable to membership inference attacks (MIAs), which aim to infer whether a data record was used to train a target model or not. To analyze and study these vulnerabilities, various…

Retrieval-Augmented Generation (RAG) is a state-of-the-art technique that mitigates issues such as hallucinations and knowledge staleness in Large Language Models (LLMs) by retrieving relevant knowledge from an external database to assist…