Skip to yearly menu bar Skip to main content


Poster

An Equivalence Between Data Poisoning and Byzantine Gradient Attacks

Sadegh Farhadkhani · Rachid Guerraoui · Lê-Nguyên Hoang · Oscar Villemaud

Hall E #1022

Keywords: [ T: Learning Theory ] [ T: Social Aspects ] [ SA: Trustworthy Machine Learning ]


Abstract:

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 of \emph{any}robust'' learning algorithm to data poisoning in highly heterogeneous applications, 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.

Chat is not available.