中文
相关论文

相关论文: White-box vs Black-box: Bayes Optimal Strategies f…

200 篇论文

Membership inference attacks are used as a key tool for disclosure auditing. They aim to infer whether an individual record was used to train a model. While such evaluations are useful to demonstrate risk, they are computationally expensive…

机器学习 · 计算机科学 2024-12-20 Anshuman Suri , Xiao Zhang , David Evans

Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference can be formalized as a hypothesis testing problem. The most…

机器学习 · 计算机科学 2023-07-10 Martin Bertran , Shuai Tang , Michael Kearns , Jamie Morgenstern , Aaron Roth , Zhiwei Steven Wu

Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service API. In providing an in-depth characterization of…

密码学与安全 · 计算机科学 2019-02-04 Stacey Truex , Ling Liu , Mehmet Emre Gursoy , Lei Yu , Wenqi Wei

Membership inference (MI) attacks exploit the fact that machine learning algorithms sometimes leak information about their training data through the learned model. In this work, we study membership inference in the white-box setting in…

机器学习 · 计算机科学 2020-06-26 Klas Leino , Matt Fredrikson

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…

密码学与安全 · 计算机科学 2022-09-01 Yiyong Liu , Zhengyu Zhao , Michael Backes , Yang Zhang

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

We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model,…

密码学与安全 · 计算机科学 2017-04-04 Reza Shokri , Marco Stronati , Congzheng Song , Vitaly Shmatikov

Diffusion models have begun to overshadow GANs and other generative models in industrial applications due to their superior image generation performance. The complex architecture of these models furnishes an extensive array of attack…

密码学与安全 · 计算机科学 2025-07-08 Yan Pang , Tianhao Wang , Xuhui Kang , Mengdi Huai , Yang Zhang

Machine learning models can leak information regarding the dataset they have trained. In this paper, we present the first membership inference attack against black-boxed object detection models that determines whether the given data records…

计算机视觉与模式识别 · 计算机科学 2020-01-29 Yeachan Park , Myungjoo Kang

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.…

机器学习 · 计算机科学 2020-09-15 Jason W. Bentley , Daniel Gibney , Gary Hoppenworth , Sumit Kumar Jha

A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well…

机器学习 · 计算机科学 2024-04-09 Anshuman Suri , Yifu Lu , Yanjin Chen , David Evans

The usage of deep learning is being escalated in many applications. Due to its outstanding performance, it is being used in a variety of security and privacy-sensitive areas in addition to conventional applications. One of the key aspects…

密码学与安全 · 计算机科学 2022-05-17 Zhaoxi Zhang , Leo Yu Zhang , Xufei Zheng , Bilal Hussain Abbasi , Shengshan Hu

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…

机器学习 · 计算机科学 2025-06-03 Yongchao Huang

With the rapid advancement of diffusion-based image-generative models, the quality of generated images has become increasingly photorealistic. Moreover, with the release of high-quality pre-trained image-generative models, a growing number…

密码学与安全 · 计算机科学 2024-09-06 Yan Pang , Tianhao Wang

Generative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks against generative models: given a data…

密码学与安全 · 计算机科学 2018-08-22 Jamie Hayes , Luca Melis , George Danezis , Emiliano De Cristofaro

In this evolving era of machine learning security, membership inference attacks have emerged as a potent threat to the confidentiality of sensitive data. In this attack, adversaries aim to determine whether a particular point was used…

机器学习 · 计算机科学 2024-06-21 Abhishek Sinha , Himanshi Tibrewal , Mansi Gupta , Nikhar Waghela , Shivank Garg

A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training dataset. These attacks are currently evaluated using…

密码学与安全 · 计算机科学 2022-04-13 Nicholas Carlini , Steve Chien , Milad Nasr , Shuang Song , Andreas Terzis , Florian Tramer

Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We design white-box inference attacks to perform a comprehensive privacy analysis of deep learning models. We measure…

机器学习 · 统计学 2020-06-09 Milad Nasr , Reza Shokri , Amir Houmansadr

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

机器学习 · 计算机科学 2022-09-14 Jiayuan Ye , Aadyaa Maddi , Sasi Kumar Murakonda , Vincent Bindschaedler , Reza Shokri

In a membership inference attack, an attacker aims to infer whether a data sample is in a target classifier's training dataset or not. Specifically, given a black-box access to the target classifier, the attacker trains a binary classifier,…

密码学与安全 · 计算机科学 2019-12-20 Jinyuan Jia , Ahmed Salem , Michael Backes , Yang Zhang , Neil Zhenqiang Gong
‹ 上一页 1 2 3 10 下一页 ›