FLAT: Latent-Driven Arbitrary-Target Backdoor Attacks in Federated Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911093810528256 |
|---|---|
| author | Nguyen, Tuan Doan, Khoa D Wong, Kok-Seng |
| author_facet | Nguyen, Tuan Doan, Khoa D Wong, Kok-Seng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04064 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FLAT: Latent-Driven Arbitrary-Target Backdoor Attacks in Federated Learning Nguyen, Tuan Doan, Khoa D Wong, Kok-Seng Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition 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. |
| title | FLAT: Latent-Driven Arbitrary-Target Backdoor Attacks in Federated Learning |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.04064 |