# Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy

arXiv: https://arxiv.org/abs/2202.09897 · HTML: https://mlsanity.com/paper/2202.09897/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 26 references that are in the map.
- First posted on arXiv 20 Feb 2022.

## Builds on (most cited first, 5 of 5)

- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation](https://mlsanity.com/paper/2010.16061/) (2020)
- [Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning](https://mlsanity.com/paper/1812.00910/) (2018)
- [Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applications](https://mlsanity.com/paper/2010.05867/) (2020)

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

- [Gaming and Cooperation in Federated Learning: What Can Happen and How to Monitor It](https://mlsanity.com/paper/2509.02391/) (2025)
- [SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacy](https://mlsanity.com/paper/2601.09460/) (2026)

## Abstract (arXiv)

Privacy-preserving federated learning enables a population of distributed clients to jointly learn a shared model while keeping client training data private, even from an untrusted server. Prior works do not provide efficient solutions that protect against collusion attacks in which parties collaborate to expose an honest client's model parameters. We present an efficient mechanism based on oblivious distributed differential privacy that is the first to protect against such client collusion, including the "Sybil" attack in which a server preferentially selects compromised devices or simulates fake devices. We leverage the novel privacy mechanism to construct a secure federated learning protocol and prove the security of that protocol. We conclude with empirical analysis of the protocol's execution speed, learning accuracy, and privacy performance on two data sets within a realistic simulation of 5,000 distributed network clients.