The Hidden Vulnerability of Distributed Learning in Byzantium

By El Mahdi El Mhamdi, Rachid Guerraoui, Sébastien Rouault. 2018

1,041 citations recorded by the source corpus.

While machine learning is going through an era of celebrated success, concerns have been raised about the vulnerability of its backbone: stochastic gradient descent (SGD). Recent approaches have been proposed to ensure the robustness of distributed SGD against adversarial (Byzantine) workers sending poisoned gradients during the training phase. Some of these approaches have been proven Byzantine-resilient: they ensure the convergence of SGD despite the presence of a minority of adversarial workers. We show in this paper that convergence is not enough. In high dimension $d \gg 1$, an adver\-sary can build on the loss function's non-convexity to make SGD converge to ineffective models. More precisely, we bring to light that existing Byzantine-resilient schemes leave a margin of poisoning of $\Omega\left(f(d)\right)$, where $f(d)$ increases at least like $\sqrt{d~}$. Based on this leeway, we build a simple attack, and experimentally show its strong to utmost effectivity on CIFAR-10 and MNIST. We introduce Bulyan, and prove it significantly reduces the attackers leeway to a narrow $O( \frac{1}{\sqrt{d~}})$ bound. We empirically show that Bulyan does not suffer the fragility of existing aggregation rules and, at a reasonable cost in terms of required batch size, achieves convergence as if only non-Byzantine gradients had been used to update the model.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Federated & Distributed Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Martin Jaggi
  2. Qiang Yang
  3. Percy Liang
  4. Philip S. Yu
  5. Yoshua Bengio
  6. Mohit Bansal
  7. Yang Liu
  8. Quoc V. Le

In Safety, Robustness & Interpretability

  1. Vitaly Shmatikov
  2. Neil Zhenqiang Gong
  3. Prateek Mittal
  4. Amir Houmansadr
  5. Reza Shokri
  6. Florian Tramèr
  7. Nicholas Carlini
  8. Dawn Song

In Federated & Distributed Learning

  1. Martin Jaggi
  2. Amir Houmansadr
  3. Qiang Yang
  4. Virat Shejwalkar
  5. Sai Praneeth Karimireddy
  6. Jianyu Wang
  7. Cong Xie
  8. Chaoyang He

Citations in the corpus