Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2507.10162 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912481467695104 |
|---|---|
| author | He, Weiyang Chang, Chip-Hong |
| author_facet | He, Weiyang Chang, Chip-Hong |
| contents | Vertical Federated Learning (VFL) enables an orchestrating active party to perform a machine learning task by cooperating with passive parties that provide additional task-related features for the same training data entities. While prior research has leveraged the privacy vulnerability of VFL to compromise its integrity through a combination of label inference and backdoor attacks, their effectiveness is constrained by the low label inference precision and suboptimal backdoor injection conditions. To facilitate a more rigorous security evaluation on VFL without these limitations, we propose HASSLE, a hijacking attack framework composed of a gradient-direction-based label inference module and an adversarial embedding generation algorithm enhanced by self-supervised learning. HASSLE accurately identifies private samples associated with a targeted label using only a single known instance of that label. In the two-party scenario, it demonstrates strong performance with an attack success rate (ASR) of over 99% across four datasets, including both image and tabular modalities, and achieves 85% ASR on the more complex CIFAR-100 dataset. Evaluation of HASSLE against 8 potential defenses further highlights its significant threat while providing new insights into building a trustworthy VFL system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10162 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HASSLE: A Self-Supervised Learning Enhanced Hijacking Attack on Vertical Federated Learning He, Weiyang Chang, Chip-Hong Cryptography and Security Vertical Federated Learning (VFL) enables an orchestrating active party to perform a machine learning task by cooperating with passive parties that provide additional task-related features for the same training data entities. While prior research has leveraged the privacy vulnerability of VFL to compromise its integrity through a combination of label inference and backdoor attacks, their effectiveness is constrained by the low label inference precision and suboptimal backdoor injection conditions. To facilitate a more rigorous security evaluation on VFL without these limitations, we propose HASSLE, a hijacking attack framework composed of a gradient-direction-based label inference module and an adversarial embedding generation algorithm enhanced by self-supervised learning. HASSLE accurately identifies private samples associated with a targeted label using only a single known instance of that label. In the two-party scenario, it demonstrates strong performance with an attack success rate (ASR) of over 99% across four datasets, including both image and tabular modalities, and achieves 85% ASR on the more complex CIFAR-100 dataset. Evaluation of HASSLE against 8 potential defenses further highlights its significant threat while providing new insights into building a trustworthy VFL system. |
| title | HASSLE: A Self-Supervised Learning Enhanced Hijacking Attack on Vertical Federated Learning |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2507.10162 |