Jump to content

Telefonaktiebolaget LM Ericsson (publ) (20250094571). GENERATIVE ADVERSARIAL-BASED ATTACK IN FEDERATED LEARNING

From WikiPatents

GENERATIVE ADVERSARIAL-BASED ATTACK IN FEDERATED LEARNING

Organization Name

Telefonaktiebolaget LM Ericsson (publ)

Inventor(s)

Jalil Taghia of Stockholm SE

Matteo Demartis of Solna SE

Konstantinos Vandikas of Solna SE

Selim Ickin of Danderyd SE

GENERATIVE ADVERSARIAL-BASED ATTACK IN FEDERATED LEARNING

This abstract first appeared for US patent application 20250094571 titled 'GENERATIVE ADVERSARIAL-BASED ATTACK IN FEDERATED LEARNING

Original Abstract Submitted

a method performed by a client node is provided for generating a generative adversarial network (gan)-based attack for disruption of a global federated learning model. the method includes setting an attack strength factor to a value; and training the gan using the attack strength factor and an initial adversarial dataset to obtain a malicious weight matrix. the initial adversarial dataset is generated from or by initial weights matrix received from a network node of the global federated learning model and initial malicious weights derived from an initial attack on the global federated learning model that used a deterministic attack to obtain the malicious weight matrix. the method further includes generating the gan-based attack including an updated malicious weight matrix; and sending the updated malicious weight matrix to the network node.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.