TrajSyn: Privacy-Preserving Dataset Distillation from Federated Model Trajectories for Server-Side Adversarial Training
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_ | 1866909966922678272 |
|---|---|
| author | Gupta, Mukur Gupta, Niharika Rahman, Saifur Pal, Shantanu Karmakar, Chandan |
| author_facet | Gupta, Mukur Gupta, Niharika Rahman, Saifur Pal, Shantanu Karmakar, Chandan |
| contents | Deep learning models deployed on edge devices are increasingly used in safety-critical applications. However, their vulnerability to adversarial perturbations poses significant risks, especially in Federated Learning (FL) settings where identical models are distributed across thousands of clients. While adversarial training is a strong defense, it is difficult to apply in FL due to strict client-data privacy constraints and the limited compute available on edge devices. In this work, we introduce TrajSyn, a privacy-preserving framework that enables effective server-side adversarial training by synthesizing a proxy dataset from the trajectories of client model updates, without accessing raw client data. We show that TrajSyn consistently improves adversarial robustness on image classification benchmarks with no extra compute burden on the client device. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_15123 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TrajSyn: Privacy-Preserving Dataset Distillation from Federated Model Trajectories for Server-Side Adversarial Training Gupta, Mukur Gupta, Niharika Rahman, Saifur Pal, Shantanu Karmakar, Chandan Machine Learning Deep learning models deployed on edge devices are increasingly used in safety-critical applications. However, their vulnerability to adversarial perturbations poses significant risks, especially in Federated Learning (FL) settings where identical models are distributed across thousands of clients. While adversarial training is a strong defense, it is difficult to apply in FL due to strict client-data privacy constraints and the limited compute available on edge devices. In this work, we introduce TrajSyn, a privacy-preserving framework that enables effective server-side adversarial training by synthesizing a proxy dataset from the trajectories of client model updates, without accessing raw client data. We show that TrajSyn consistently improves adversarial robustness on image classification benchmarks with no extra compute burden on the client device. |
| title | TrajSyn: Privacy-Preserving Dataset Distillation from Federated Model Trajectories for Server-Side Adversarial Training |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.15123 |