FLAT: Latent-Driven Arbitrary-Target Backdoor Attacks in Federated Learning

TL;DR

FLAT introduces a flexible, latent-driven backdoor attack in federated learning that generates diverse, target-specific triggers, challenging existing defenses and emphasizing the need for new protective strategies.

Contribution

The paper presents FLAT, a novel attack method using a latent-driven autoencoder to create adaptive, multi-target triggers without retraining, enhancing attack diversity and stealth.

Findings

FLAT achieves high attack success rates.

It remains robust against advanced defenses.

Triggers are visually adaptive and highly variable.

Abstract

Federated learning (FL) is vulnerable to backdoor attacks, yet most existing methods are limited by fixed-pattern or single-target triggers, making them inflexible and easier to detect. We propose FLAT (FL Arbitrary-Target Attack), a novel backdoor attack that leverages a latent-driven conditional autoencoder to generate diverse, target-specific triggers as needed. By introducing a latent code, FLAT enables the creation of visually adaptive and highly variable triggers, allowing attackers to select arbitrary targets without retraining and to evade conventional detection mechanisms. Our approach unifies attack success, stealth, and diversity within a single framework, introducing a new level of flexibility and sophistication to backdoor attacks in FL. Extensive experiments show that FLAT achieves high attack success and remains robust against advanced FL defenses. These results highlight the urgent need for new defense strategies to address latent-driven, multi-target backdoor threats in federated settings.