English
Related papers

Related papers: Confidence-Ranked Reconstruction of Census Microda…

200 papers

Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated…

Machine Learning · Computer Science 2022-05-31 Joceline Ziegler , Bjarne Pfitzner , Heinrich Schulz , Axel Saalbach , Bert Arnrich

Data reconstruction attacks on machine learning models pose a substantial threat to privacy, potentially leaking sensitive information. Although defending against such attacks using differential privacy (DP) provides theoretical guarantees,…

Machine Learning · Computer Science 2025-03-11 Kristian Schwethelm , Johannes Kaiser , Moritz Knolle , Sarah Lockfisch , Daniel Rueckert , Alexander Ziller

Decentralized Gradient Descent (D-GD) allows a set of users to perform collaborative learning without sharing their data by iteratively averaging local model updates with their neighbors in a network graph. The absence of direct…

Machine Learning · Computer Science 2024-06-05 Abdellah El Mrini , Edwige Cyffers , Aurélien Bellet

This study investigates privacy leakage in dimensionality reduction methods through a novel machine learning-based reconstruction attack. Employing an informed adversary threat model, we develop a neural network capable of reconstructing…

Cryptography and Security · Computer Science 2025-06-03 Chayadon Lumbut , Donlapark Ponnoprat

The purpose of anonymizing structured data is to protect the privacy of individuals in the data while retaining the statistical properties of the data. An important class of attack on anonymized data is attribute inference, where an…

Cryptography and Security · Computer Science 2025-07-03 Paul Francis , David Wagner

Rounding confidence score is considered trivial but a simple and effective countermeasure to stop gradient descent based image reconstruction attacks. However, its capability in the face of more sophisticated reconstruction attacks is an…

Computer Vision and Pattern Recognition · Computer Science 2020-09-07 Hadi Mansourifar , Weidong Shi

The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the training set can be reconstructed directly from model parameters.…

Machine Learning · Computer Science 2025-09-26 Yehonatan Refael , Guy Smorodinsky , Ofir Lindenbaum , Itay Safran

We consider the power of linear reconstruction attacks in statistical data privacy, showing that they can be applied to a much wider range of settings than previously understood. Linear attacks have been studied before (Dinur and Nissim…

Data Structures and Algorithms · Computer Science 2012-10-09 Shiva Prasad Kasiviswanathan , Mark Rudelson , Adam Smith

In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized data collection. Concomitant with this rise in…

Machine Learning · Statistics 2019-06-04 Abhishek Bhowmick , John Duchi , Julien Freudiger , Gaurav Kapoor , Ryan Rogers

The success of DNNs has driven the extensive applications of person re-identification (ReID) into a new era. However, whether ReID inherits the vulnerability of DNNs remains unexplored. To examine the robustness of ReID systems is rather…

Computer Vision and Pattern Recognition · Computer Science 2020-04-10 Hongjun Wang , Guangrun Wang , Ya Li , Dongyu Zhang , Liang Lin

In this paper, we initiate the study of local model reconstruction attacks for federated learning, where a honest-but-curious adversary eavesdrops the messages exchanged between a targeted client and the server, and then reconstructs the…

Machine Learning · Computer Science 2024-05-28 Ilias Driouich , Chuan Xu , Giovanni Neglia , Frederic Giroire , Eoin Thomas

Reconstruction attacks against federated learning (FL) aim to reconstruct users' samples through users' uploaded gradients. Local differential privacy (LDP) is regarded as an effective defense against various attacks, including sample…

Cryptography and Security · Computer Science 2025-02-13 Zhichao You , Xuewen Dong , Shujun Li , Ximeng Liu , Siqi Ma , Yulong Shen

Natural language processing (NLP) models have become increasingly popular in real-world applications, such as text classification. However, they are vulnerable to privacy attacks, including data reconstruction attacks that aim to extract…

Computation and Language · Computer Science 2023-06-27 Adel Elmahdy , Ahmed Salem

Differentially private training offers a protection which is usually interpreted as a guarantee against membership inference attacks. By proxy, this guarantee extends to other threats like reconstruction attacks attempting to extract…

Cryptography and Security · Computer Science 2023-10-31 Jamie Hayes , Saeed Mahloujifar , Borja Balle

Cryptographic approaches, such as secure multiparty computation, can be used to compute in a secure manner the function of a distributed graph without centralizing the data of each participant. However, the output of the protocol itself can…

Cryptography and Security · Computer Science 2024-12-09 Sofiane Azogagh , Zelma Aubin Birba , Josée Desharnais , Sébastien Gambs , Marc-Olivier Killijian , Nadia Tawbi

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…

Machine Learning · Computer Science 2020-04-21 Yuheng Zhang , Ruoxi Jia , Hengzhi Pei , Wenxiao Wang , Bo Li , Dawn Song

Although powerful graph neural networks (GNNs) have boosted numerous real-world applications, the potential privacy risk is still underexplored. To close this gap, we perform the first comprehensive study of graph reconstruction attack that…

Machine Learning · Computer Science 2023-06-16 Zhanke Zhou , Chenyu Zhou , Xuan Li , Jiangchao Yao , Quanming Yao , Bo Han

Federated Learning (FL) trains a black-box and high-dimensional model among different clients by exchanging parameters instead of direct data sharing, which mitigates the privacy leak incurred by machine learning. However, FL still suffers…

Machine Learning · Computer Science 2024-03-05 Qi Tan , Qi Li , Yi Zhao , Zhuotao Liu , Xiaobing Guo , Ke Xu

Graph Neural Networks (GNNs) achieve high performance across many applications but function as black-box models, limiting their use in critical domains like healthcare and criminal justice. Explainability methods address this by providing…

Machine Learning · Computer Science 2025-06-04 Rishi Raj Sahoo , Rucha Bhalchandra Joshi , Subhankar Mishra

With the rise of large foundation models, split inference (SI) has emerged as a popular computational paradigm for deploying models across lightweight edge devices and cloud servers, addressing data privacy and computational cost concerns.…

Machine Learning · Computer Science 2025-09-16 Wa-Kin Lei , Jun-Cheng Chen , Shang-Tse Chen