中文
相关论文

相关论文: Mitigating Privacy Risk in Membership Inference by…

200 篇论文

Machine unlearning is a newly popularized technique for removing specific training data from a trained model, enabling it to comply with data deletion requests. While it protects the rights of users requesting unlearning, it also introduces…

机器学习 · 计算机科学 2025-12-19 Lulu Xue , Shengshan Hu , Linqiang Qian , Peijin Guo , Yechao Zhang , Minghui Li , Yanjun Zhang , Dayong Ye , Leo Yu Zhang

Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet companies to deploy machine learning as a service (MLaaS).…

密码学与安全 · 计算机科学 2018-12-18 Ahmed Salem , Yang Zhang , Mathias Humbert , Pascal Berrang , Mario Fritz , Michael Backes

Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obtain confidential information about the data used for…

密码学与安全 · 计算机科学 2025-03-13 Daniel Jiménez-López , Nuria Rodríguez-Barroso , M. Victoria Luzón , Francisco Herrera

Membership Inference Attacks have emerged as a dominant method for empirically measuring privacy leakage from machine learning models. Here, privacy is measured by the {\em{advantage}} or gap between a score or a function computed on the…

机器学习 · 计算机科学 2024-05-27 Ruihan Wu , Pengrun Huang , Kamalika Chaudhuri

We study the privacy implications of training recurrent neural networks (RNNs) with sensitive training datasets. Considering membership inference attacks (MIAs), which aim to infer whether or not specific data records have been used in…

密码学与安全 · 计算机科学 2023-01-23 Yunhao Yang , Parham Gohari , Ufuk Topcu

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…

计算机视觉与模式识别 · 计算机科学 2023-11-17 Thomas Cilloni , Charles Fleming , Charles Walter

Machine learning models leak information about the datasets on which they are trained. An adversary can build an algorithm to trace the individual members of a model's training dataset. As a fundamental inference attack, he aims to…

机器学习 · 统计学 2018-07-17 Milad Nasr , Reza Shokri , Amir Houmansadr

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…

机器学习 · 统计学 2026-05-27 Valentin Dorseuil , Jamal Atif , Olivier Cappé

The success of deep neural networks has driven numerous research studies and applications from Euclidean to non-Euclidean data. However, there are increasing concerns about privacy leakage, as these networks rely on processing private data.…

机器学习 · 计算机科学 2025-11-03 Zhanke Zhou , Jianing Zhu , Fengfei Yu , Xuan Li , Xiong Peng , Tongliang Liu , Bo Han

Since machine learning model is often trained on a limited data set, the model is trained multiple times on the same data sample, which causes the model to memorize most of the training set data. Membership Inference Attacks (MIAs) exploit…

机器学习 · 计算机科学 2024-11-19 Depeng Chen , Xiao Liu , Jie Cui , Hong Zhong

Membership inference attacks (MIAs) aim to infer whether a data point has been used to train a machine learning model. These attacks can be employed to identify potential privacy vulnerabilities and detect unauthorized use of personal data.…

机器学习 · 计算机科学 2023-10-03 Myeongseob Ko , Ming Jin , Chenguang Wang , Ruoxi Jia

Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This article provides theoretical guarantees by exploring the…

机器学习 · 统计学 2025-10-08 Eric Aubinais , Elisabeth Gassiat , Pablo Piantanida

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…

机器学习 · 计算机科学 2020-07-20 Shruti Tople , Amit Sharma , Aditya Nori

The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…

机器学习 · 统计学 2019-08-27 Liwei Song , Reza Shokri , Prateek Mittal

Deep learning models, while achieving remarkable performances, are vulnerable to membership inference attacks (MIAs). Although various defenses have been proposed, there is still substantial room for improvement in the privacy-utility…

密码学与安全 · 计算机科学 2025-09-29 Yuefeng Peng , Ali Naseh , Amir Houmansadr

Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of…

密码学与安全 · 计算机科学 2026-02-03 Marlon Tobaben , Hibiki Ito , Joonas Jälkö , Yuan He , Antti Honkela

With the widespread application of large language models (LLM), concerns about the privacy leakage of model training data have increasingly become a focus. Membership Inference Attacks (MIAs) have emerged as a critical tool for evaluating…

机器人学 · 计算机科学 2024-12-24 Zichen Song , Sitan Huang , Zhongfeng Kang

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…

密码学与安全 · 计算机科学 2020-09-02 Shadi Rahimian , Tribhuvanesh Orekondy , Mario Fritz

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

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