International Business Machines Corporation

Kamala Micaela Noelle Varma

Nathalie Baracaldo Angel

Yi Zhou

Ali Anwar

Syed Amer Zawad

A computer-implemented method, a computer program product, and a computer system for defending against adversarial attacks in federated learning. In the federated learning comprising an aggregator and parties, the aggregator receives weights sent from the respective parties. The aggregator computes values of a performance metric for weight arrays obtained by the respective parties, using a validation dataset. The aggregator ranks the values of the performance metric in a list. The aggregator recursively splits the list in half until one or more adversary updates of the weights are isolated. The aggregator excludes one or more parties that send the one or more adversary updates from participating in a current round of training in the federated learning.

Defending against adversarial attacks in federated learning

A federated learning method comprises creating a log of previously provided gradients from a plurality of workers, receiving updated gradients from the plurality of workers, calculating a vulnerability weight for each layer of a global machine learning model using the updated gradients, calculating an aggregated gradient using the vulnerability weight and the updated gradients, and updating the global machine learning model using the aggregated gradient. Some embodiments may also determine whether a Byzantine attack is occurring based upon the calculated aggregated gradient. An apparatus and computer program product may be used to implement the method.

Growing community of inventors

Minneapolis, MN, United States of America

Kamala Micaela Noelle Varma