English
Related papers

Related papers: Analysing Training-Data Leakage from Gradients thr…

200 papers

Being able to reconstruct training data from the parameters of a neural network is a major privacy concern. Previous works have shown that reconstructing training data, under certain circumstances, is possible. In this work, we analyse such…

While prior work has shown that Federated Learning updates can leak sensitive information, label reconstruction attacks, which aim to recover input labels from shared gradients, have not yet been examined in the context of Human Activity…

Machine Learning · Computer Science 2025-08-08 Marius Bock , Maximilian Hopp , Kristof Van Laerhoven , Michael Moeller

Training deep neural networks via federated learning allows clients to share, instead of the original data, only the model trained on their data. Prior work has demonstrated that in practice a client's private information, unrelated to the…

Cryptography and Security · Computer Science 2021-06-01 Fan Mo , Anastasia Borovykh , Mohammad Malekzadeh , Hamed Haddadi , Soteris Demetriou

We propose Gradient Inversion Transcript (GIT), a novel generative approach for reconstructing training data from leaked gradients. GIT employs a generative attack model, whose architecture is tailored to align with the structure of the…

Machine Learning · Computer Science 2025-05-27 Xinping Chen , Chen Liu

Distributed machine learning has been widely used in recent years to tackle the large and complex dataset problem. Therewith, the security of distributed learning has also drawn increasing attentions from both academia and industry. In this…

Machine Learning · Computer Science 2022-06-13 Zihao Zhao , Mengen Luo , Wenbo Ding

Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a central server without exchanging their private data.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Zhuohang Li , Jiaxin Zhang , Luyang Liu , Jian Liu

Federated learning has emerged as a prominent privacy-preserving technique for leveraging large-scale distributed datasets by sharing gradients instead of raw data. However, recent studies indicate that private training data can still be…

Cryptography and Security · Computer Science 2025-09-30 Tamer Ahmed Eltaras , Qutaibah Malluhi , Alessandro Savino , Stefano Di Carlo , Adnan Qayyum

Current methods for reconstructing training data from trained classifiers are restricted to very small models, limited training set sizes, and low-resolution images. Such restrictions hinder their applicability to real-world scenarios. In…

Machine Learning · Computer Science 2024-07-23 Yakir Oz , Gilad Yehudai , Gal Vardi , Itai Antebi , Michal Irani , Niv Haim

The Deep Leakage from Gradient (DLG) attack has emerged as a prevalent and highly effective method for extracting sensitive training data by inspecting exchanged gradients. This approach poses a substantial threat to the privacy of…

Machine Learning · Computer Science 2023-11-27 Chenyang Li , Zhao Song , Weixin Wang , Chiwun Yang

Federated Learning (FL) is a widely adopted privacy-preserving machine learning approach where private data remains local, enabling secure computations and the exchange of local model gradients between local clients and third-party…

Machine Learning · Computer Science 2025-08-04 Hanchi Ren , Jingjing Deng , Xianghua Xie

Federated learning enables multiple users to build a joint model by sharing their model updates (gradients), while their raw data remains local on their devices. In contrast to the common belief that this provides privacy benefits, we here…

We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself. Our results speak to a tension between the desire to keep a proprietary model secret and the ability to offer model…

Machine Learning · Statistics 2018-07-16 Smitha Milli , Ludwig Schmidt , Anca D. Dragan , Moritz Hardt

Understanding to what extent neural networks memorize training data is an intriguing question with practical and theoretical implications. In this paper we show that in some cases a significant fraction of the training data can in fact be…

Machine Learning · Computer Science 2022-12-06 Niv Haim , Gal Vardi , Gilad Yehudai , Ohad Shamir , Michal Irani

It is widely believed that sharing gradients will not leak private training data in distributed learning systems such as Collaborative Learning and Federated Learning, etc. Recently, Zhu et al. presented an approach which shows the…

Machine Learning · Computer Science 2020-01-09 Bo Zhao , Konda Reddy Mopuri , Hakan Bilen

Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show…

Machine Learning · Statistics 2021-02-18 Sasi Kumar Murakonda , Reza Shokri , George Theodorakopoulos

As the scale and size of the data increases significantly nowadays, federal learning (Bonawitz et al. [2019]) for high performance computing and machine learning has been much more important than ever before (Abadi et al. [2016]). People…

Machine Learning · Computer Science 2022-11-16 Yanchong Zheng

Federated learning (FL) enables collaborative model training among multiple clients without the need to expose raw data. Its ability to safeguard privacy, at the heart of FL, has recently been a hot-button debate topic. To elaborate,…

Machine Learning · Computer Science 2025-06-11 Mingyuan Fan , Fuyi Wang , Cen Chen , Jianying Zhou

Publicly releasing the specification of a model with its trained parameters means an adversary can attempt to reconstruct information about the training data via training data reconstruction attacks, a major vulnerability of modern machine…

Machine Learning · Statistics 2025-07-25 George Wynne

Federated learning has emerged as a promising paradigm for collaborative model training while preserving data privacy. However, recent studies have shown that it is vulnerable to various privacy attacks, such as data reconstruction attacks.…

Cryptography and Security · Computer Science 2024-07-25 Xiaojin Zhang , Wei Chen

Federated Learning (FL) is designed to prevent data leakage through collaborative model training without centralized data storage. However, it remains vulnerable to gradient reconstruction attacks that recover original training data from…

Machine Learning · Computer Science 2024-11-07 Yuxiao Chen , Gamze Gürsoy , Qi Lei