Federated Learning Privacy

We study attacks on federated learning systems that aim to compromise user privacy, violating the key promise of this paradigm.

Blog Posts

The Role of Red Teaming in PETs

Our team won the Red Teaming category of the U.S. PETs Prize Challenge, a competition centered around federated learning.

Publications

2025

GRAIN: Exact Graph Reconstruction from Gradients

Maria Drencheva, Ivo Petrov, Maximilian Baader, Dimitar I. Dimitrov, Martin Vechev

ICLR 2025

Paper

2024

DAGER: Exact Gradient Inversion for Large Language Models

Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin Vechev

NeurIPS 2024

Poster
Slides
Paper
Code

SPEAR: Exact Gradient Inversion of Batches in Federated Learning

Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin Vechev

NeurIPS 2024

Poster
Slides
Paper

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning

Kostadin Garov, Dimitar I. Dimitrov, Nikola Jovanović, Martin Vechev

ICLR 2024

Paper
Code

2023

TabLeak: Tabular Data Leakage in Federated Learning

Mark Vero, Mislav Balunović, Dimitar I. Dimitrov, Martin Vechev

ICML 2023

Paper
Code

2022

LAMP: Extracting Text from Gradients with Language Model Priors

Mislav Balunović*, Dimitar I. Dimitrov*, Nikola Jovanović, Martin Vechev

NeurIPS 2022 * Equal contribution

Blog
Paper
Code

Data Leakage in Federated Averaging

Dimitar I. Dimitrov, Mislav Balunović, Nikola Konstantinov, Martin Vechev

TMLR 2022

Paper
Code

Bayesian Framework for Gradient Leakage

Mislav Balunović, Dimitar I. Dimitrov, Robin Staab, Martin Vechev

ICLR 2022

Blog
Paper
Code