中文
相关论文

相关论文: Protection Against Reconstruction and Its Applicat…

200 篇论文

Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that collects the local gradient information instead of real data.…

密码学与安全 · 计算机科学 2021-05-24 Lichao Sun , Jianwei Qian , Xun Chen

Nowadays, the development of information technology is growing rapidly. In the big data era, the privacy of personal information has been more pronounced. The major challenge is to find a way to guarantee that sensitive personal information…

机器学习 · 计算机科学 2022-10-17 Mengde Han , Tianqing Zhu , Wanlei Zhou

Differential privacy (DP) is by far the most widely accepted framework for mitigating privacy risks in machine learning. However, exactly how small the privacy parameter $\epsilon$ needs to be to protect against certain privacy risks in…

机器学习 · 计算机科学 2023-08-11 Chuan Guo , Alexandre Sablayrolles , Maziar Sanjabi

Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model. It has been recently shown that simple heuristics can reconstruct data samples from language models, making this…

机器学习 · 计算机科学 2022-02-16 Pierre Stock , Igor Shilov , Ilya Mironov , Alexandre Sablayrolles

Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in different applications such as big data analysis, graph data…

密码学与安全 · 计算机科学 2021-12-06 Honglu Jiang , Yifeng Gao , S M Sarwar , Luis GarzaPerez , Mahmudul Robin

Collaborative inference has recently emerged as an attractive framework for applying deep learning to Internet of Things (IoT) applications by splitting a DNN model into several subpart models among resource-constrained IoT devices and the…

密码学与安全 · 计算机科学 2022-11-22 Jihyeon Ryu , Yifeng Zheng , Yansong Gao , Sharif Abuadbba , Junyaup Kim , Dongho Won , Surya Nepal , Hyoungshick Kim , Cong Wang

Differential privacy is known to protect against threats to validity incurred due to adaptive, or exploratory, data analysis -- even when the analyst adversarially searches for a statistical estimate that diverges from the true value of the…

密码学与安全 · 计算机科学 2022-07-25 Elbert Du , Cynthia Dwork

Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…

机器学习 · 计算机科学 2021-08-17 Xue Yang , Yan Feng , Weijun Fang , Jun Shao , Xiaohu Tang , Shu-Tao Xia , Rongxing Lu

Given access to a machine learning model, can an adversary reconstruct the model's training data? This work studies this question from the lens of a powerful informed adversary who knows all the training data points except one. By…

密码学与安全 · 计算机科学 2022-04-26 Borja Balle , Giovanni Cherubin , Jamie Hayes

The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…

机器学习 · 计算机科学 2018-02-20 Aurélien Bellet , Rachid Guerraoui , Mahsa Taziki , Marc Tommasi

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…

密码学与安全 · 计算机科学 2021-10-13 Jiaxiang Liu , Simon Oya , Florian Kerschbaum

Scientific collaborations benefit from collaborative learning of distributed sources, but remain difficult to achieve when data are sensitive. In recent years, privacy preserving techniques have been widely studied to analyze distributed…

密码学与安全 · 计算机科学 2022-06-30 Guanhong Miao , A. Adam Ding , Samuel S. Wu

Commercial companies that collect user data on a large scale have been the main beneficiaries of this trend since the success of deep learning techniques is directly proportional to the amount of data available for training. Massive data…

密码学与安全 · 计算机科学 2020-06-30 Saichethan Miriyala Reddy , Saisree Miriyala

Privacy attacks on machine learning models aim to identify the data that is used to train such models. Such attacks, traditionally, are studied on static models that are trained once and are accessible by the adversary. Motivated to meet…

机器学习 · 计算机科学 2022-02-09 Ji Gao , Sanjam Garg , Mohammad Mahmoody , Prashant Nalini Vasudevan

The performance of differentially private machine learning can be boosted significantly by leveraging the transfer learning capabilities of non-private models pretrained on large public datasets. We critically review this approach. We…

机器学习 · 计算机科学 2024-07-18 Florian Tramèr , Gautam Kamath , Nicholas Carlini

Data privacy has emerged as an important issue as data-driven deep learning has been an essential component of modern machine learning systems. For instance, there could be a potential privacy risk of machine learning systems via the model…

机器学习 · 计算机科学 2019-11-25 Taihong Xiao , Yi-Hsuan Tsai , Kihyuk Sohn , Manmohan Chandraker , Ming-Hsuan Yang

Collaborative learning has gained great popularity due to its benefit of data privacy protection: participants can jointly train a Deep Learning model without sharing their training sets. However, recent works discovered that an adversary…

计算机视觉与模式识别 · 计算机科学 2021-03-30 Wei Gao , Shangwei Guo , Tianwei Zhang , Han Qiu , Yonggang Wen , Yang Liu

Real-world data is usually segmented by attributes and distributed across different parties. Federated learning empowers collaborative training without exposing local data or models. As we demonstrate through designed attacks, even with a…

机器学习 · 计算机科学 2021-04-30 Shuang Zhang , Liyao Xiang , Xi Yu , Pengzhi Chu , Yingqi Chen , Chen Cen , Li Wang

Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks. However, sharing models pre-trained on potentially sensitive data is prone to…

计算与语言 · 计算机科学 2025-08-14 Ying Yin , Ivan Habernal

Learning a privacy-preserving model from sensitive data which are distributed across multiple devices is an increasingly important problem. The problem is often formulated in the federated learning context, with the aim of learning a single…

机器学习 · 计算机科学 2023-04-20 Mikko A. Heikkilä , Matthew Ashman , Siddharth Swaroop , Richard E. Turner , Antti Honkela
‹ 上一页 1 2 3 10 下一页 ›