# Can collaborative learning be private, robust and scalable?

arXiv: https://arxiv.org/abs/2205.02652 · HTML: https://mlsanity.com/paper/2205.02652/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 5 May 2022.

## Builds on (most cited first, 18 of 18)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Certified Robustness to Adversarial Examples with Differential Privacy](https://mlsanity.com/paper/1802.03471/) (2018)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization](https://mlsanity.com/paper/1909.13014/) (2019)
- [Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack](https://mlsanity.com/paper/1907.02044/) (2019)
- [Defensive Quantization: When Efficiency Meets Robustness](https://mlsanity.com/paper/1904.08444/) (2019)
- [Extending Defensive Distillation](https://mlsanity.com/paper/1705.05264/) (2017)
- [QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks](https://mlsanity.com/paper/1811.01437/) (2018)
- [Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes](https://mlsanity.com/paper/2110.13541/) (2021)
- [Defend Deep Neural Networks Against Adversarial Examples via Fixed and Dynamic Quantized Activation Functions](https://mlsanity.com/paper/1807.06714/) (2018)
- [Adversarial Attack on Deep Product Quantization Network for Image Retrieval](https://mlsanity.com/paper/2002.11374/) (2020)
- [Improved Gradient based Adversarial Attacks for Quantized Networks](https://mlsanity.com/paper/2003.13511/) (2020)
- [Is PGD-Adversarial Training Necessary? Alternative Training via a Soft-Quantization Network with Noisy-Natural Samples Only](https://mlsanity.com/paper/1810.05665/) (2018)

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

- [Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimation](https://mlsanity.com/paper/2211.00724/) (2022)
- [Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis](https://mlsanity.com/paper/2210.10886/) (2022)

## Abstract (arXiv)

In federated learning for medical image analysis, the safety of the learning protocol is paramount. Such settings can often be compromised by adversaries that target either the private data used by the federation or the integrity of the model itself. This requires the medical imaging community to develop mechanisms to train collaborative models that are private and robust against adversarial data. In response to these challenges, we propose a practical open-source framework to study the effectiveness of combining differential privacy, model compression and adversarial training to improve the robustness of models against adversarial samples under train- and inference-time attacks. Using our framework, we achieve competitive model performance, a significant reduction in model's size and an improved empirical adversarial robustness without a severe performance degradation, critical in medical image analysis.