Leverage Variational Graph Representation For Model Poisoning on Federated Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909179813298176 |
|---|---|
| author | Li, Kai Yuan, Xin Zheng, Jingjing Ni, Wei Dressler, Falko Jamalipour, Abbas |
| author_facet | Li, Kai Yuan, Xin Zheng, Jingjing Ni, Wei Dressler, Falko Jamalipour, Abbas |
| contents | This paper puts forth a new training data-untethered model poisoning (MP) attack on federated learning (FL). The new MP attack extends an adversarial variational graph autoencoder (VGAE) to create malicious local models based solely on the benign local models overheard without any access to the training data of FL. Such an advancement leads to the VGAE-MP attack that is not only efficacious but also remains elusive to detection. VGAE-MP attack extracts graph structural correlations among the benign local models and the training data features, adversarially regenerates the graph structure, and generates malicious local models using the adversarial graph structure and benign models' features. Moreover, a new attacking algorithm is presented to train the malicious local models using VGAE and sub-gradient descent, while enabling an optimal selection of the benign local models for training the VGAE. Experiments demonstrate a gradual drop in FL accuracy under the proposed VGAE-MP attack and the ineffectiveness of existing defense mechanisms in detecting the attack, posing a severe threat to FL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15042 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leverage Variational Graph Representation For Model Poisoning on Federated Learning Li, Kai Yuan, Xin Zheng, Jingjing Ni, Wei Dressler, Falko Jamalipour, Abbas Cryptography and Security Artificial Intelligence This paper puts forth a new training data-untethered model poisoning (MP) attack on federated learning (FL). The new MP attack extends an adversarial variational graph autoencoder (VGAE) to create malicious local models based solely on the benign local models overheard without any access to the training data of FL. Such an advancement leads to the VGAE-MP attack that is not only efficacious but also remains elusive to detection. VGAE-MP attack extracts graph structural correlations among the benign local models and the training data features, adversarially regenerates the graph structure, and generates malicious local models using the adversarial graph structure and benign models' features. Moreover, a new attacking algorithm is presented to train the malicious local models using VGAE and sub-gradient descent, while enabling an optimal selection of the benign local models for training the VGAE. Experiments demonstrate a gradual drop in FL accuracy under the proposed VGAE-MP attack and the ineffectiveness of existing defense mechanisms in detecting the attack, posing a severe threat to FL. |
| title | Leverage Variational Graph Representation For Model Poisoning on Federated Learning |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2404.15042 |