paper-with-me

Papers

Attacks to Federated Learning: Responsive Web User Interface to Recover Training Data from User Gradients

2020-06-08 · Hans Albert Lianto, Yang Zhao, Jun Zhao

Local differential privacy (LDP) is an emerging privacy standard to protect individual user data. One scenario where LDP can be applied is federated learning, where each user sends in his/her user gradients to an aggregator who uses these gradients to perform stochastic gradient descent. In a case where the aggregator is untrusted and LDP is not applied to each user gradient, the aggregator can recover sensitive user data from these gradients. In this paper, we present a new interactive web demo showcasing the power of local differential privacy by visualizing federated learning with local differential privacy. Moreover, the live demo shows how LDP can prevent untrusted aggregators from recovering sensitive training data. A measure called the exp-hamming recovery is also created to show the extent of how much data the aggregator can recover.

📄 PDF Abstract BibTeX arXiv:2006.04695

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Data Leakage in Federated Averaging

2022-06-24 · Dimitar I. Dimitrov, Mislav Balunović, Nikola Konstantinov, Martin Vechev

Recent attacks have shown that user data can be recovered from FedSGD updates, thus breaking privacy. However, these attacks are of limited practical relevance as federated learning typically uses the FedAvg algorithm. C…

Federated Learning

Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix

2021-06-10 · Maximilian Lam, Gu-Yeon Wei, David Brooks, Vijay Janapa Reddi 외

We show that aggregated model updates in federated learning may be insecure. An untrusted central server may disaggregate user updates from sums of updates across participants given repeated observations, enabling the se…

Federated Learning

Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification

2022-02-01 · Yuxin Wen, Jonas Geiping, Liam Fowl, Micah Goldblum 외

Federated learning (FL) has rapidly risen in popularity due to its promise of privacy and efficiency. Previous works have exposed privacy vulnerabilities in the FL pipeline by recovering user data from gradient updates. …

Federated Learning

Cascading Gradient Inversion via LT-Code Inspired Peeling in Federated Learning

2026-09-09 · Saeed Shariati, Mohsen Alambardar Meybodi arxiv

Federated learning shares model updates rather than raw data, yet these updates can be inverted to reconstruct the clients' training data. Analytic reconstruction attacks, which invert a gradient in closed form, degrade …

Federated Learning

Enhanced Web User Interface Design Via Cross-Device Responsiveness Assessment Using An Improved HCI-INTEGRATED DL Schemes

2025-12-13 · Shrinivass Arunachalam Balasubramanian arxiv

User Interface (UI) optimization is essential in the digital era to enhance user satisfaction in web environments. Nevertheless, the existing UI optimization models had overlooked the Cross-Responsiveness (CR) assessment…