# SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection

Source: [SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection](<https://www.sota2.com/research/paper/68fa72581e209131cea55d0b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:24:11.561Z

Authors: Nasimeh Heydaribeni, Ruisi Zhang, Tara Javidi, Cristina Nita-Rotaru, Farinaz Koushanfar

Published: 2023-08-04T23:51:05.000Z

## Abstract

In this work, we introduce SureFED, a novel framework for byzantine robust federated learning. Unlike many existing defense methods that rely on statistically robust quantities, making them vulnerable to stealthy and colluding attacks, SureFED establishes trust using the local information of benign clients. SureFED utilizes an uncertainty aware model evaluation and introspection to safeguard against poisoning attacks. In particular, each client independently trains a clean local model exclusively using its local dataset, acting as the reference point for evaluating model updates. SureFED leverages Bayesian models that provide model uncertainties and play a crucial role in the model evaluation process. Our framework exhibits robustness even when the majority of clients are compromised, remains agnostic to the number of malicious clients, and is well-suited for non-IID settings. We theoretically prove the robustness of our algorithm against data and model poisoning attacks in a decentralized linear regression setting. Proof-of Concept evaluations on benchmark image classification data demonstrate the superiority of SureFED over the state of the art defense methods under various colluding and non-colluding data and model poisoning attacks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2308.02747>)

[PDF](<https://arxiv.org/pdf/2308.02747.pdf>)
