paper-with-me

Papers

Can collaborative learning be private, robust and scalable?

2022-05-05 · Dmitrii Usynin, Helena Klause, Johannes C. Paetzold, Daniel Rueckert, Georgios Kaissis

In federated learning for medical image analysis, the safety of the learning protocol is paramount. Such settings can often be compromised by adversaries that target either the private data used by the federation or the integrity of the model itself. This requires the medical imaging community to develop mechanisms to train collaborative models that are private and robust against adversarial data. In response to these challenges, we propose a practical open-source framework to study the effectiveness of combining differential privacy, model compression and adversarial training to improve the robustness of models against adversarial samples under train- and inference-time attacks. Using our framework, we achieve competitive model performance, a significant reduction in model's size and an improved empirical adversarial robustness without a severe performance degradation, critical in medical image analysis.

📄 PDF Abstract BibTeX arXiv:2205.02652

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessFederated LearningMedical Image AnalysisModel Compression

Similar Papers 제목 키워드 기반

MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games

2026-02-27 · Jacob Eisenstein, Fantine Huot, Adam Fisch, Jonathan Berant 외 arxiv

We present a scalable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require effective communication about private information. This enables an interactiv…

Federated User Representation Learning

2019-09-27 · ICLR 2020 1 · Duc Bui, Kshitiz Malik, Jack Goetz, Honglei Liu 외

Collaborative personalization, such as through learned user representations (embeddings), can improve the prediction accuracy of neural-network-based models significantly. We propose Federated User Representation Learnin…

Federated LearningPrivacy PreservingRepresentation Learning

Private Matrix Factorization with Public Item Features

2023-09-17 · Mihaela Curmei, Walid Krichene, Li Zhang, Mukund Sundararajan

We consider the problem of training private recommendation models with access to public item features. Training with Differential Privacy (DP) offers strong privacy guarantees, at the expense of loss in recommendation qu…

Collaborative Filtering

HLF-FSL. A Decentralized Federated Split Learning Solution for IoT on Hyperledger Fabric

2025-07-10 · Carlos Beis Penedo, Rebeca P. Díaz Redondo, Ana Fernández Vilas, Manuel Fernández Veiga 외

Collaborative machine learning in sensitive domains demands scalable, privacy preserving solutions for enterprise deployment. Conventional Federated Learning (FL) relies on a central server, introducing single points of …

Federated LearningPrivacy Preserving

A Scalable Approach for Privacy-Preserving Collaborative Machine Learning

2020-11-03 · NeurIPS 2020 12 · Jinhyun So, Basak Guler, A. Salman Avestimehr

We consider a collaborative learning scenario in which multiple data-owners wish to jointly train a logistic regression model, while keeping their individual datasets private from the other parties. We propose COPML, a f…

BIG-bench Machine LearningPrivacy Preserving