# FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning

Source: [FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning](<https://www.sota2.com/research/paper/68fa7a711e209131cea83425>)

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

Data updated: 2026-07-03T05:00:04.966Z

Authors: Tuan Nguyen, Sze Jue Yang, Khoa D. Doan, Chee Seng Chan, Kok-Seng Wong

Published: 2025-08-06T03:54:29.000Z

## Abstract

Horizontal federated learning (HFL) backdoor audits often summarize model behavior through clean accuracy (CA), mean attack success rate (ASR), or a single known-trigger test. Such summaries can hide a different failure mode, in which one target label is activated by many trigger realizations. We study this failure mode with FLAT, a latent-conditioned reliability stress test for HFL backdoors. In FLAT, compromised clients still submit ordinary classifier updates to the server, while an attacker-side generator $G(x,t,z)$ separates target intent $t$ from trigger realization $z$. This separation shifts the audit question from whether one known trigger succeeds to how the hidden behavior varies across targets, latent samples, defenses, and post-stop rounds. On CIFAR-10, CIFAR-100, and Tiny-ImageNet, FLAT preserves clean utility while reaching 99.49%, 99.66%, and 94.10% single-target FedAvg ASR. The evaluation also reveals non-uniform defense responses, where a server rule can suppress one target mode while leaving another active. These observations motivate HFL backdoor audits that report target-wise ASR, worst-target ASR, target coverage, latent-sampled behavior, post-stop persistence, and defense response.

## 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/2508.04064>)

[PDF](<https://arxiv.org/pdf/2508.04064.pdf>)
