# On the Robustness of Distributed Machine Learning against Transfer Attacks

arXiv: https://arxiv.org/abs/2412.14080 · HTML: https://mlsanity.com/paper/2412.14080/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 18 Dec 2024.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [Enhancing the Transferability of Adversarial Attacks through Variance Tuning](https://mlsanity.com/paper/2103.15571/) (2021)
- [Improving Adversarial Robustness via Promoting Ensemble Diversity](https://mlsanity.com/paper/1901.08846/) (2019)
- [Admix: Enhancing the Transferability of Adversarial Attacks](https://mlsanity.com/paper/2102.00436/) (2021)
- [Adversarial Attacks and Defences Competition](https://mlsanity.com/paper/1804.00097/) (2018)
- [Rethinking Model Ensemble in Transfer-based Adversarial Attacks](https://mlsanity.com/paper/2303.09105/) (2023)
- [Backpropagating Linearly Improves Transferability of Adversarial Examples](https://mlsanity.com/paper/2012.03528/) (2020)
- [On Generating Transferable Targeted Perturbations](https://mlsanity.com/paper/2103.14641/) (2021)
- [Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability](https://mlsanity.com/paper/2004.14861/) (2020)
- [Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input](https://mlsanity.com/paper/2203.09123/) (2022)
- [Transferable Adversarial Attack based on Integrated Gradients](https://mlsanity.com/paper/2205.13152/) (2022)
- [Feature Space Targeted Attacks by Statistic Alignment](https://mlsanity.com/paper/2105.11645/) (2021)
- [Decentralized Learning Made Easy with DecentralizePy](https://mlsanity.com/paper/2304.08322/) (2023)
- [Beware the Black-Box: on the Robustness of Recent Defenses to Adversarial Examples](https://mlsanity.com/paper/2006.10876/) (2020)
- [Transfer Attacks Revisited: A Large-Scale Empirical Study in Real Computer Vision Settings](https://mlsanity.com/paper/2204.04063/) (2022)

## Abstract (arXiv)

Although distributed machine learning (distributed ML) is gaining considerable attention in the community, prior works have independently looked at instances of distributed ML in either the training or the inference phase. No prior work has examined the combined robustness stemming from distributing both the learning and the inference process. In this work, we explore, for the first time, the robustness of distributed ML models that are fully heterogeneous in training data, architecture, scheduler, optimizer, and other model parameters. Supported by theory and extensive experimental validation using CIFAR10 and FashionMNIST, we show that such properly distributed ML instantiations achieve across-the-board improvements in accuracy-robustness tradeoffs against state-of-the-art transfer-based attacks that could otherwise not be realized by current ensemble or federated learning instantiations. For instance, our experiments on CIFAR10 show that for the Common Weakness attack, one of the most powerful state-of-the-art transfer-based attacks, our method improves robust accuracy by up to 40%, with a minimal impact on clean task accuracy.