An Equivalence Between Data Poisoning and Byzantine Gradient Attacks

by   Sadegh Farhadkhani, et al.

To study the resilience of distributed learning, the "Byzantine" literature considers a strong threat model where workers can report arbitrary gradients to the parameter server. Whereas this model helped obtain several fundamental results, it has sometimes been considered unrealistic, when the workers are mostly trustworthy machines. In this paper, we show a surprising equivalence between this model and data poisoning, a threat considered much more realistic. More specifically, we prove that every gradient attack can be reduced to data poisoning, in any personalized federated learning system with PAC guarantees (which we show are both desirable and realistic). This equivalence makes it possible to obtain new impossibility results on the resilience to data poisoning as corollaries of existing impossibility theorems on Byzantine machine learning. Moreover, using our equivalence, we derive a practical attack that we show (theoretically and empirically) can be very effective against classical personalized federated learning models.



page 1

page 2

page 3

page 4


Holdout SGD: Byzantine Tolerant Federated Learning

This work presents a new distributed Byzantine tolerant federated learni...

LEGATO: A LayerwisE Gradient AggregaTiOn Algorithm for Mitigating Byzantine Attacks in Federated Learning

Federated learning has arisen as a mechanism to allow multiple participa...

Federated Learning via Plurality Vote

Federated learning allows collaborative workers to solve a machine learn...

Byzantine-Resilient Secure Federated Learning

Secure federated learning is a privacy-preserving framework to improve m...

Byzantine-Robust Learning on Heterogeneous Datasets via Resampling

In Byzantine robust distributed optimization, a central server wants to ...

Fast and Secure Distributed Learning in High Dimension

Modern machine learning is distributed and the work of several machines ...

ByzShield: An Efficient and Robust System for Distributed Training

Training of large scale models on distributed clusters is a critical com...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.