# Long-term Data Sharing under Exclusivity Attacks

arXiv: https://arxiv.org/abs/2201.09137 · HTML: https://mlsanity.com/paper/2201.09137/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 48 references that are in the map.
- First posted on arXiv 22 Jan 2022.

## Builds on (most cited first, 15 of 15)

- [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)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Federated Machine Learning: Concept and Applications](https://mlsanity.com/paper/1902.04885/) (2019)
- [Distributed learning of deep neural network over multiple agents](https://mlsanity.com/paper/1810.06060/) (2018)
- [One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning](https://mlsanity.com/paper/2103.03228/) (2021)
- [Optimum Statistical Estimation with Strategic Data Sources](https://mlsanity.com/paper/1408.2539/) (2014)
- [Distributed linear regression by averaging](https://mlsanity.com/paper/1810.00412/) (2018)
- [Decentralized & Collaborative AI on Blockchain](https://mlsanity.com/paper/1907.07247/) (2019)
- [Properties of Multiwinner Voting Rules](https://mlsanity.com/paper/1506.02891/) (2015)
- [Mechanism Design for Facility Location Problems: A Survey](https://mlsanity.com/paper/2106.03457/) (2021)
- [Regression Equilibrium](https://mlsanity.com/paper/1905.02576/) (2019)
- [Fast and Robust Least Squares Estimation in Corrupted Linear Models](https://mlsanity.com/paper/1406.3175/) (2014)
- [Linear Regression from Strategic Data Sources](https://mlsanity.com/paper/1309.7824/) (2013)
- [Cheating by Duplication: Equilibrium Requires Global Knowledge](https://mlsanity.com/paper/1711.04728/) (2017)

## Built on by (most cited first, 1 of 1)

- [Prediction-sharing During Training and Inference](https://mlsanity.com/paper/2403.17515/) (2024)

## Abstract (arXiv)

The quality of learning generally improves with the scale and diversity of data. Companies and institutions can therefore benefit from building models over shared data. Many cloud and blockchain platforms, as well as government initiatives, are interested in providing this type of service. These cooperative efforts face a challenge, which we call ``exclusivity attacks''. A firm can share distorted data, so that it learns the best model fit, but is also able to mislead others. We study protocols for long-term interactions and their vulnerability to these attacks, in particular for regression and clustering tasks. We conclude that the choice of protocol, as well as the number of Sybil identities an attacker may control, is material to vulnerability.