Skip to content

On the Limits of Privacy in Federated Learning: Personalization and Adversarial Analysis

TL;DR

This thesis demonstrates that federated learning should not be considered inherently private merely because data remain decentralized, and introduces a personalized privacy-preserving federated learning framework that allows individual clients to select their preferred privacy mechanism and protection level.

View source

Similar papers

Conference Oct 2026

Privacy-Preserving Techniques in Federated Learning: A Comprehensive Survey and Critical Review

Federated Learning (FL) is a distributed machine learning paradigm in which multiple clients collaboratively train a model while their raw data remains local. Despite this design, FL is exposed to privacy risks such as inference attacks, model inversion, membership inference, and gradient leakage, which threaten sensit...

M. Bhuvaneswari, B. Pavani · 0 citations
Preprint Nov 2026

A Novel Federated Learning Framework for Defending Against Gradient Inversion Attacks

Federated Learning (FL) offers a paradigm for collaborative machine learning model training among clients, preserving data privacy by avoiding direct data sharing. However, the gradient information exchanged in FL has been shown to be vulnerable to Gradient Inversion Attacks (GIA), which can reconstruct sensitive user...

Peng-Xin Guo, Zi-Ying Huang, Shuang Zeng et al. · 0 citations
Review Open access Oct 2026

Federated and Privacy-Preserving Machine Learning: Methods and Trade-offs

Federated learning trains a shared model across many decentralized clients while keeping raw data on the device, which addresses data silos and tightening privacy regulation such as GDPR and HIPAA. This paper reviews the methods and the practical trade-offs of federated and privacy-preserving machine learning. The disc...

Saritha E · 0 citations
Conference Oct 2026

Privacy-Preserving Intrusion Detection using Federated Learning and Tabular Generative Adversarial Networks

In this research, a solution towards private data collaboration through Federated Learning (FL), Conditional Tabular Generative Adversarial Networks (CTGAN), and Differential Privacy (DP) is investigated. This solution allows organisations to collaborate on model training without exchanging their original network traff...

Bipin Maharjan, Pritika, B. Shanmugam · 0 citations
Conference Oct 2026

Game Theory for Security, Privacy, and Trustworthiness in Federated Learning: A Systematization of Knowledge

Rather than aggregating private datasets at a central server, Federated Learning (FL) facilitates localized, collaborative Machine Learning (ML) training, thereby reducing communication overhead and maintaining strict data privacy. Due to these structural advantages, FL has been broadly integrated into fields such as h...

Atul Anand, Alperen Örsdemir, Alptekin Kupcu · 0 citations
Preprint Oct 2026

Combining Homomorphic Encryption and Differential Privacy in Federated Learning for Model Inspection and Availability

The increasing prevalence of decentralized data has led to a growing interest in federated learning, which enables collaborative model training without clients sharing their sensitive local data. However, FL alone does not sufficiently protect sensitive training data and is generally coupled with privacy-preserving tec...

Ceren Yildirim, K. Kaya, Sinan Yıldırım et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.