# Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning

arXiv: https://arxiv.org/abs/1805.05838 · HTML: https://mlsanity.com/paper/1805.05838/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2018.

## Built on by (most cited first, 15 of 15)

- [FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks](https://mlsanity.com/paper/2111.11066/) (2021)
- [Federated Learning Challenges and Opportunities: An Outlook](https://mlsanity.com/paper/2202.00807/) (2022)
- [PIVODL: Privacy-preserving vertical federated learning over distributed labels](https://mlsanity.com/paper/2108.11444/) (2021)
- [Efficient and Reliable Overlay Networks for Decentralized Federated Learning](https://mlsanity.com/paper/2112.15486/) (2021)
- [Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions](https://mlsanity.com/paper/2406.10861/) (2024)
- [Semi-Supervised Federated Peer Learning for Skin Lesion Classification](https://mlsanity.com/paper/2103.03703/) (2021)
- [Technical Report: Assisting Backdoor Federated Learning with Whole Population Knowledge Alignment](https://mlsanity.com/paper/2207.12327/) (2022)
- [Data Origin Inference in Machine Learning](https://mlsanity.com/paper/2211.13416/) (2022)
- [Privacy-preserving Object Detection](https://mlsanity.com/paper/2103.06587/) (2021)
- [Statistical Privacy Guarantees of Machine Learning Preprocessing Techniques](https://mlsanity.com/paper/2109.02496/) (2021)
- [The More, the Better? A Study on Collaborative Machine Learning for DGA Detection](https://mlsanity.com/paper/2109.11830/) (2021)
- [Aggregation Weighting of Federated Learning via Generalization Bound Estimation](https://mlsanity.com/paper/2311.05936/) (2023)
- [Sensing and Mapping for Better Roads: Initial Plan for Using Federated Learning and Implementing a Digital Twin to Identify the Road Conditions in a Developing Country -- Sri Lanka](https://mlsanity.com/paper/2107.14551/) (2021)
- [Private Training Set Inspection in MLaaS](https://mlsanity.com/paper/2305.09058/) (2023)
- [Privacy Attack in Federated Learning is Not Easy: An Experimental Study](https://mlsanity.com/paper/2409.19301/) (2024)

## Abstract (arXiv)

Federated Learning (FL) systems are gaining popularity as a solution to training Machine Learning (ML) models from large-scale user data collected on personal devices (e.g., smartphones) without their raw data leaving the device. At the core of FL is a network of anonymous user devices sharing training information (model parameter updates) computed locally on personal data. However, the type and degree to which user-specific information is encoded in the model updates is poorly understood. In this paper, we identify model updates encode subtle variations in which users capture and generate data. The variations provide a strong statistical signal, allowing an adversary to effectively deanonymize participating devices using a limited set of auxiliary data. We analyze resulting deanonymization attacks on diverse tasks on real-world (anonymized) user-generated data across a range of closed- and open-world scenarios. We study various strategies to mitigate the risks of deanonymization. As random perturbation methods do not offer convincing operating points, we propose data-augmentation strategies which introduces adversarial biases in device data and thereby, offer substantial protection against deanonymization threats with little effect on utility.