paper-with-me

홈 › Papers

Profiling Privacy Preservation Against Gradient Inversion Attacks in Tabular Federated Learning

2026-05-31 · Ivo Osterberg Nilsson, Maximilian Birr Engvall, Viktor Valadi, Teddy Lazebnik arxiv

Federated learning (FL) enables multiple data holders to train machine learning models collaboratively without centralizing raw data, making it useful in privacy sensitive domains such as healthcare and institutional data sharing. FL keeps data local to clients while communicating only model updates, such as gradients or model deltas. Nevertheless, these updates can expose private client data through gradient inversion attacks (GIAs). We study this risk for tabular FL under an honest-but-curious server threat model across FL protocols, client batch sizes, training stages, attacker assumptions, model architectures, and binary classification, multiclass classification, and regression tasks. We use MIMIC-IV and complementary benchmark datasets. Our evaluation distinguishes numerical and categorical recovery, baseline recoverability, feature level recovery, and exact match rate (EMR). We evaluate FedSGD gradients and FedAvg model deltas with an exposure aligned protocol, comparing attacked models after matched client data exposure rather than matched communication rounds. We compare multilayer perceptron (MLP), ResNet, and FT-Transformer models, and isolate architecture effects through an MLP grid over width, depth, activation, normalization, and dropout. The results show that small client batches and updates representing few distinct records are most vulnerable. Larger local batches and stronger aggregation reduce reconstruction but do not eliminate leakage. FT-Transformer is consistently harder to invert than one-hot baselines, while reconstructability also varies substantially within the MLP family. These findings identify architecture as a practical privacy variable in tabular FL. We also show that aggregate reconstruction accuracy can overstate complete record recovery in sparse data, making EMR and baseline comparisons essential.

📄 PDF Abstract BibTeX arXiv:2606.00986

Code (0)

등록된 구현이 없습니다.

Tasks

Binary ClassificationFederated Learning

Similar Papers 제목 키워드 기반

Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation

2023-01-01 · ICCV 2023 1 · Guangnian Wan, Haitao Du, Xuejing Yuan, Jun Yang 외

Federated learning (FL) is a privacy-enhanced distributed machine learning framework, in which multiple clients collaboratively train a global model by exchanging their model updates without sharing local private dat…

Federated Learning

Evaluating Gradient Inversion Attacks and Defenses in Federated Learning

2021-11-30 · NeurIPS 2021 12 · Yangsibo Huang, Samyak Gupta, Zhao Song, Kai Li 외

Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recove…

Federated Learning

AFGI: Towards Accurate and Fast-convergent Gradient Inversion Attack in Federated Learning

2024-03-13 · Can Liu, Jin Wang, and Yipeng Zhou, Yachao Yuan 외

Federated learning (FL) empowers privacypreservation in model training by only exposing users' model gradients. Yet, FL users are susceptible to gradient inversion attacks (GIAs) which can reconstruct ground-truth traini…

Edge DetectionFederated Learning

On the utility and protection of optimization with differential privacy and classic regularization techniques

2022-09-07 · Eugenio Lomurno, Matteo Matteucci

Nowadays, owners and developers of deep learning models must consider stringent privacy-preservation rules of their training data, usually crowd-sourced and retaining sensitive information. The most widely adopted method…

Deep LearningL2 RegularizationPrivacy Preserving

GI-SMN: Gradient Inversion Attack against Federated Learning without Prior Knowledge

2024-05-06 · Jin Qian, Kaimin Wei, Yongdong Wu, Jilian Zhang 외

Federated learning (FL) has emerged as a privacy-preserving machine learning approach where multiple parties share gradient information rather than original user data. Recent work has demonstrated that gradient inversion…

Federated LearningPrivacy Preserving