Turning Privacy-preserving Mechanisms against Federated Learning

05/09/2023
by   Marco Arazzi, et al.
0

Recently, researchers have successfully employed Graph Neural Networks (GNNs) to build enhanced recommender systems due to their capability to learn patterns from the interaction between involved entities. In addition, previous studies have investigated federated learning as the main solution to enable a native privacy-preserving mechanism for the construction of global GNN models without collecting sensitive data into a single computation unit. Still, privacy issues may arise as the analysis of local model updates produced by the federated clients can return information related to sensitive local data. For this reason, experts proposed solutions that combine federated learning with Differential Privacy strategies and community-driven approaches, which involve combining data from neighbor clients to make the individual local updates less dependent on local sensitive data. In this paper, we identify a crucial security flaw in such a configuration, and we design an attack capable of deceiving state-of-the-art defenses for federated learning. The proposed attack includes two operating modes, the first one focusing on convergence inhibition (Adversarial Mode), and the second one aiming at building a deceptive rating injection on the global federated model (Backdoor Mode). The experimental results show the effectiveness of our attack in both its modes, returning on average 60 fully effective backdoors in 93 Mode.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/10/2023

Vertical Federated Graph Neural Network for Recommender System

Conventional recommender systems are required to train the recommendatio...
research
05/27/2023

Privacy-Preserving Model Aggregation for Asynchronous Federated Learning

We present a novel privacy-preserving model aggregation for asynchronous...
research
10/20/2020

Mitigating Sybil Attacks on Differential Privacy based Federated Learning

In federated learning, machine learning and deep learning models are tra...
research
03/07/2023

A Privacy Preserving System for Movie Recommendations using Federated Learning

Recommender systems have become ubiquitous in the past years. They solve...
research
06/17/2023

Federated Learning Based Distributed Localization of False Data Injection Attacks on Smart Grids

Data analysis and monitoring on smart grids are jeopardized by attacks o...
research
03/01/2023

FedScore: A privacy-preserving framework for federated scoring system development

We propose FedScore, a privacy-preserving federated learning framework f...
research
08/08/2023

Pelta: Shielding Transformers to Mitigate Evasion Attacks in Federated Learning

The main premise of federated learning is that machine learning model up...

Please sign up or login with your details

Forgot password? Click here to reset