相关论文: Quantifying Membership Inference Vulnerability via…

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…

While Membership Inference Attacks (MIAs) are the prevailing method for identifying training data, their application has expanded into privacy auditing and machine unlearning. Nevertheless, the field lacks a systematic framework for…

Neural models for vulnerability prediction (VP) have achieved impressive performance by learning from large-scale code repositories. However, their susceptibility to Membership Inference Attacks (MIAs), where adversaries aim to infer…

Membership inference attacks (MIAs) are widely used to assess the privacy risks associated with machine learning models. However, when these attacks are applied to pre-trained large language models (LLMs), they encounter significant…

Membership inference attacks (MIA) aim to infer whether a particular data point is part of the training dataset of a model. In this paper, we propose a new task in the context of LLM privacy: entity-level discovery of membership risk…

Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such…

The large model size, high computational operations, and vulnerability against membership inference attack (MIA) have impeded deep learning or deep neural networks (DNNs) popularity, especially on mobile devices. To address the challenge,…

Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's training dataset. Existing attack methods have commonly…

With the emergence of powerful large-scale foundation models, the training paradigm is increasingly shifting from from-scratch training to transfer learning. This enables high utility training with small, domain-specific datasets typical in…

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…

Membership inference attacks (MIAs) reveal whether specific data was used to train machine learning models, serving as important tools for privacy auditing and compliance assessment. Recent studies have reported that MIAs perform only…

Recently, diffusion models have achieved remarkable success in generating tasks, including image and audio generation. However, like other generative models, diffusion models are prone to privacy issues. In this paper, we propose an…

The lack of data transparency in Large Language Models (LLMs) has highlighted the importance of Membership Inference Attack (MIA), which differentiates trained (member) and untrained (non-member) data. Though it shows success in previous…

Membership inference determines, given a sample and trained parameters of a machine learning model, whether the sample was part of the training set. In this paper, we derive the optimal strategy for membership inference with a few…

Membership inference attacks (MIAs) aim to determine whether a specific example was used to train a given language model. While prior work has explored prompt-based attacks such as ReCALL, these methods rely heavily on the assumption that…

Membership inference attacks aim to detect if a particular data point was used in training a model. We design a novel statistical test to perform robust membership inference attacks (RMIA) with low computational overhead. We achieve this by…

With the rapid advancements of large-scale text-to-image diffusion models, various practical applications have emerged, bringing significant convenience to society. However, model developers may misuse the unauthorized data to train…

Membership inference attacks serves as useful tool for fair use of language models, such as detecting potential copyright infringement and auditing data leakage. However, many current state-of-the-art attacks require access to models'…

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…

Membership Inference Attack (MIA) aims to determine whether a specific data sample was included in the training dataset of a target model. Traditional MIA approaches rely on shadow models to mimic target model behavior, but their…