中文
相关论文

相关论文: A hierarchical approach for assessing the vulnerab…

200 篇论文

Membership inference attacks (MIAs) have emerged as the standard tool for evaluating the privacy risks of AI models. However, state-of-the-art attacks require training numerous, often computationally expensive, reference models, limiting…

机器学习 · 计算机科学 2025-10-23 Euodia Dodd , Nataša Krčo , Igor Shilov , Yves-Alexandre de Montjoye

The pervasive deployment of deep learning models across critical domains has concurrently intensified privacy concerns due to their inherent propensity for data memorization. While Membership Inference Attacks (MIAs) serve as the gold…

机器学习 · 计算机科学 2026-04-16 Chihan Huang , Huaijin Wang , Shuai Wang

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…

机器学习 · 计算机科学 2024-09-24 Noam Koren , Abigail Goldsteen , Guy Amit , Ariel Farkash

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

密码学与安全 · 计算机科学 2020-12-10 Liwei Song , Prateek Mittal

A Membership Inference Attack (MIA) assesses how much a target machine learning model reveals about its training data by determining whether specific query instances were part of the training set. State-of-the-art MIAs rely on training…

密码学与安全 · 计算机科学 2026-01-13 Yuntao Du , Yuetian Chen , Hanshen Xiao , Bruno Ribeiro , Ninghui Li

Membership Inference Attacks (MIAs) are currently a dominant approach for evaluating privacy in machine learning applications. Despite their significance in identifying records belonging to the training dataset, several concerns remain…

机器学习 · 计算机科学 2026-01-23 Cristina Pêra , Tânia Carvalho , Maxime Cordy , Luís Antunes

An over-the-air membership inference attack (MIA) is presented to leak private information from a wireless signal classifier. Machine learning (ML) provides powerful means to classify wireless signals, e.g., for PHY-layer authentication. As…

密码学与安全 · 计算机科学 2021-07-27 Yi Shi , Yalin E. Sagduyu

A number of recent works have demonstrated that API access to machine learning models leaks information about the dataset records used to train the models. Further, the work of \cite{somesh-overfit} shows that such membership inference…

密码学与安全 · 计算机科学 2019-10-15 Benjamin Zi Hao Zhao , Hassan Jameel Asghar , Raghav Bhaskar , Mohamed Ali Kaafar

While in-processing fairness approaches show promise in mitigating biased predictions, their potential impact on privacy leakage remains under-explored. We aim to address this gap by assessing the privacy risks of fairness-enhanced binary…

机器学习 · 计算机科学 2025-05-29 Huan Tian , Guangsheng Zhang , Bo Liu , Tianqing Zhu , Ming Ding , Wanlei Zhou

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…

Training machine learning models on privacy-sensitive data has become a popular practice, driving innovation in ever-expanding fields. This has opened the door to new attacks that can have serious privacy implications. One such attack, the…

密码学与安全 · 计算机科学 2023-06-16 Thomas Humphries , Simon Oya , Lindsey Tulloch , Matthew Rafuse , Ian Goldberg , Urs Hengartner , Florian Kerschbaum

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…

机器学习 · 计算机科学 2025-09-03 Hengyu Wu , Yang Cao

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…

信号处理 · 电气工程与系统科学 2020-06-26 Yi Shi , Kemal Davaslioglu , Yalin E. Sagduyu

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…

密码学与安全 · 计算机科学 2025-01-22 Cong Wu , Jing Chen , Qianru Fang , Kun He , Ziming Zhao , Hao Ren , Guowen Xu , Yang Liu , Yang Xiang

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…

机器学习 · 统计学 2024-06-13 Sajjad Zarifzadeh , Philippe Liu , Reza Shokri

Among all privacy attacks against Machine Learning (ML), membership inference attacks (MIA) attracted the most attention. In these attacks, the attacker is given an ML model and a data point, and they must infer whether the data point was…

密码学与安全 · 计算机科学 2025-12-02 Bram van Dartel , Marc Damie , Florian Hahn

Deep learning models often raise privacy concerns as they leak information about their training data. This enables an adversary to determine whether a data point was in a model's training set by conducting a membership inference attack…

机器学习 · 计算机科学 2020-06-11 Yigitcan Kaya , Sanghyun Hong , Tudor Dumitras

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,…

信息检索 · 计算机科学 2022-06-29 Zihan Wang , Na Huang , Fei Sun , Pengjie Ren , Zhumin Chen , Hengliang Luo , Maarten de Rijke , Zhaochun Ren

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…

机器学习 · 计算机科学 2025-09-11 Jiashu Tao , Reza Shokri

Language Models (LMs) typically adhere to a "pre-training and fine-tuning" paradigm, where a universal pre-trained model can be fine-tuned to cater to various specialized domains. Low-Rank Adaptation (LoRA) has gained the most widespread…

密码学与安全 · 计算机科学 2025-07-25 Delong Ran , Xinlei He , Tianshuo Cong , Anyu Wang , Qi Li , Xiaoyun Wang