Related papers: Disparate Vulnerability to Membership Inference At…

The increasing prominence of deep learning applications and reliance on personalized data underscore the urgent need to address privacy vulnerabilities, particularly Membership Inference Attacks (MIAs). Despite numerous MIA studies,…

Membership inference attacks (MIAs) have become the standard tool for evaluating privacy leakage in machine learning (ML). Among them, the Likelihood-Ratio Attack (LiRA) is widely regarded as the state of the art when sufficient shadow…

The membership inference attack (MIA) is a popular paradigm for compromising the privacy of a machine learning (ML) model. MIA exploits the natural inclination of ML models to overfit upon the training data. MIAs are trained to distinguish…

Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not. Existing MIAs designed for large language models (LLMs) can be bifurcated into two types: reference-free and…

Membership Inference Attacks (MIAs) are widely used to quantify training data memorization and assess privacy risks. Standard evaluation requires repeated retraining, which is computationally costly for large models. One-run methods (single…

As large-scale models such as Large Language Models (LLMs) and Large Multimodal Models (LMMs) see increasing deployment, their privacy risks remain underexplored. Membership Inference Attacks (MIAs), which reveal whether a data point was…

Determining whether a dataset was part of a machine learning model's training data pool can reveal privacy vulnerabilities, a challenge often addressed through membership inference attacks (MIAs). Traditional MIAs typically require access…

This paper introduces a novel approach to membership inference attacks (MIA) targeting stable diffusion computer vision models, specifically focusing on the highly sophisticated Stable Diffusion V2 by StabilityAI. MIAs aim to extract…

Model explanations improve the transparency of black-box machine learning (ML) models and their decisions; however, they can also be exploited to carry out privacy threats such as membership inference attacks (MIA). Existing works have only…

Membership inference attacks (MIAs) aim to determine whether a specific data point was part of a model's training set, serving as effective tools for evaluating privacy leakage of vision models. However, existing MIAs implicitly assume…

Machine learning (ML) models are vulnerable to membership inference attacks (MIAs), which determine whether a given input is used for training the target model. While there have been many efforts to mitigate MIAs, they often suffer from…

Learned recommender systems may inadvertently leak information about their training data, leading to privacy violations. We investigate privacy threats faced by recommender systems through the lens of membership inference. In such attacks,…

Membership Inference Attacks (MIAs) have emerged as a principled framework for auditing the privacy of synthetic data generated by tabular generative models, where many diverse methods have been proposed that each exploit different privacy…

Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted approaches by a wide margin. Motivated by this observation, we address the following question: can the…

Federated Learning enables collaborative learning among clients via a coordinating server while avoiding direct data sharing, offering a perceived solution to preserve privacy. However, recent studies on Membership Inference Attacks (MIAs)…

Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model's training data, remain…

This paper presents how to leak private information from a wireless signal classifier by launching an over-the-air membership inference attack (MIA). As machine learning (ML) algorithms are used to process wireless signals to make decisions…

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…

A Membership Inference Attack (MIA) assesses how much a trained machine learning model reveals about its training data by determining whether specific query instances were included in the dataset. We classify existing MIAs into adaptive or…

Machine learning models can inadvertently expose confidential properties of their training data, making them vulnerable to membership inference attacks (MIA). While numerous evaluation methods exist, many require computationally expensive…