Implementation of FedAVG (McMahan, Brendan, et al. 'Communication-efficient learning of deep networks from decentralized data.' Artificial intelligenc

Server of FedAVG for single process simulation Args: clients ([FedAvgClient]): a list of FedAVG clients. global_model (torch.nn.M

torch.Tensor-like object for Paillier Encryption

General Gradient Inversion Attacker model inversion attack based on gradients can be written as follows: x^* = argmin_x' L_grad(x': W

Client of FedAVG for single process simulation Args: model (torch.nn.Module): local model user_id (int, optional): if of this cli

This class allows you to convert numpy.array to torch.Dataset Args: x (np.array): y (np.array): transform (torch.transfor

Implementation of SGD to update the global model of Federated Learning. Args: parameters (List[torch.nn.Parameter]): parameters of the mo

Implementation of Adam to update the global model of Federated Learning. Args: parameters (List[torch.nn.Parameter]): parameters of the m

Generalized class for computing the privacy budget using the Moments Accountant technique.

Hungarian algorithm implementation for solving the assignment problem.

Manager class for privatizing DPSGD (Differentially Private Stochastic Gradient Descent) optimization. Args: accountant: Privacy acc

* @brief DataFrame Class * */

Implementation of 'Jhunjhunwala, Divyansh, Shiqiang Wang, and Gauri Joshi. "FedExP: Speeding up Federated Averaging Via Extrapolation." arXiv preprint

Implementation of FedKD (https://arxiv.org/abs/2108.13323)

Custom exception class for flickering detection.

Manager class for FoolsGold proposed in https://arxiv.org/abs/1808.04866.

Manager class for Free-Rider Attack (https://arxiv.org/abs/1911.12560)

Manager class for GAN based model inversion attack (https://arxiv.org/abs/1702.07464)

Implementation of history attack proposed in https://arxiv.org/pdf/2203.08669.pdf

Implementation of MAPF proposed in https://arxiv.org/pdf/2203.08669.pdf

Implementation of model inversion attack reference: https://dl.acm.org/doi/pdf/10.1145/2810103.2813677 Attributes: target_model: mode

Client of MOON for single process simulation (Li, Qinbin, Bingsheng He, and Dawn Song. "Model-contrastive federated learning." Proceedings of

Implementation of K. LeFevre, D. J. DeWitt and R. Ramakrishnan, 'Mondrian Multidimensional K-Anonymity,' 22nd International Conference on Data Eng

Custom assertion error class for multi-box assertions

Client Manager for secure aggregation with Paillier Encryption

Train shadow models for membership inference reference https://arxiv.org/abs/1610.05820 Args models : torch models for shadow

Client-side Manager for sparse gradients.

Server-side Manager for sparse gradients.

Variational Information Bottleneck (VIB) module. Args: encoder (torch.nn.Module): Encoder module. decoder (torch.nn.Module):

Manager class for privatizing AdaDPS (Adaptive Differentially Private Stochastic Gradient Descent) optimization. Args: accountant: P

Implementation of AdaDPS proposed in `Private Adaptive Optimization with Side information` (https://arxiv.org/pdf/2202.05963.pdf)

Abstract class foe the client of collaborative learning. Args: model (torch.nn.Module): a local model user_id (int, optional): id

Abstract class for API of federated learning with knowledge distillation. Args: server (aijack.collaborative.core.BaseServer): the server

Basic class for optimizers of the server in Federated Learning. Args: parameters (List[torch.nn.Parameter]): parameters of the model

Abstract class for Federated Learning API

Abstract class for Manager API

Base class for computing the privacy budget using the Moments Accountant technique.

Abstract class for the server of the collaborative learning. Args: clients (List[BaseClient]): a list of clients server_model (to