# Location Leakage in Federated Signal Maps

arXiv: https://arxiv.org/abs/2112.03452 · HTML: https://mlsanity.com/paper/2112.03452/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 85 references that are in the map.
- First posted on arXiv 7 Dec 2021.

## Builds on (most cited first, 23 of 23)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning](https://mlsanity.com/paper/1702.07464/) (2017)
- [On the Convergence of Local Descent Methods in Federated Learning](https://mlsanity.com/paper/1910.14425/) (2019)
- [LDP-Fed: Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2006.03637/) (2020)
- [FedVision: An Online Visual Object Detection Platform Powered by Federated Learning](https://mlsanity.com/paper/2001.06202/) (2020)
- [Knock Knock, Who's There? Membership Inference on Aggregate Location Data](https://mlsanity.com/paper/1708.06145/) (2017)
- [LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning](https://mlsanity.com/paper/2109.14236/) (2021)
- [On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them](https://mlsanity.com/paper/2006.08403/) (2020)
- [Long-Term Mobile Traffic Forecasting Using Deep Spatio-Temporal Neural Networks](https://mlsanity.com/paper/1712.08083/) (2017)
- [FLeet: Online Federated Learning via Staleness Awareness and Performance Prediction](https://mlsanity.com/paper/2006.07273/) (2020)
- [Spatial Signal Strength Prediction using 3D Maps and Deep Learning](https://mlsanity.com/paper/2011.03597/) (2020)
- [Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregation](https://mlsanity.com/paper/2111.02356/) (2021)
- [On (The Lack Of) Location Privacy in Crowdsourcing Applications](https://mlsanity.com/paper/1901.04923/) (2019)

## Built on by (most cited first, 2 of 2)

- [Privacy-Utility Trades in Crowdsourced Signal Map Obfuscation](https://mlsanity.com/paper/2201.04782/) (2022)
- [A Unified Prediction Framework for Signal Maps](https://mlsanity.com/paper/2202.03679/) (2022)

## Abstract (arXiv)

We consider the problem of predicting cellular network performance (signal maps) from measurements collected by several mobile devices. We formulate the problem within the online federated learning framework: (i) federated learning (FL) enables users to collaboratively train a model, while keeping their training data on their devices; (ii) measurements are collected as users move around over time and are used for local training in an online fashion. We consider an honest-but-curious server, who observes the updates from target users participating in FL and infers their location using a deep leakage from gradients (DLG) type of attack, originally developed to reconstruct training data of DNN image classifiers. We make the key observation that a DLG attack, applied to our setting, infers the average location of a batch of local data, and can thus be used to reconstruct the target users' trajectory at a coarse granularity. We build on this observation to protect location privacy, in our setting, by revisiting and designing mechanisms within the federated learning framework including: tuning the FL parameters for averaging, curating local batches so as to mislead the DLG attacker, and aggregating across multiple users with different trajectories. We evaluate the performance of our algorithms through both analysis and simulation based on real-world mobile datasets, and we show that they achieve a good privacy-utility tradeoff.