The combination of Deep Learning (DL) and Federated Learning (FL) makes it a popular paradigm to train powerful models securely on large-scale data in a distributed way. However, current solutions face challenges such as significant communication overheads for clients with limited resources, potential privacy risks arising from FL's distributed nature, and the inability to maintain model accuracy without loss under high compression ratios. To solve these issues, we propose a lightweight Communication-efficient and Privacy-preserving FL scheme CPFL by designing Cyclic Segmented Compressive Sensing (CSCS) and using efficient Symmetric Homomorphic Encryption (SHE), which greatly reduces the number of transmitted model weights without sacrificing model accuracy. Formal analysis shows the security of CPFL against known-plaintext attacks and ensures model convergence. Extensive experiments demonstrate that CPFL achieves remarkable model accuracy under more than 200× compression ratio, and even reduces the communication cost by 99.5% compared with previous solutions.

In the era of Internet of Things (IoT) and federated learning (FL), where distributed training models are essential, the FL paradigm has come into the spotlight for researchers. However, the inconsistency in the sources of client data and non-independent and identically distributed (Non-IID) heterogeneous characteristics lead to loss in model accuracy. Existing method which attempts to homogenize data distribution among clients based on generative adversarial networks (GANs) incurs high computation overheads on clients in IoT. In this article, we propose a lightweight feature prototype knowledge transfer (FPKT) mechanism. By capturing the essence of data categories, FPKT generates pseudo-features without requiring the original data features, thereby efficiently enhancing model accuracy. We formally prove that FPKT resists chosen plaintext attack (CPA) and experiments demonstrate that our scheme achieves a hundredfold increase in computational efficiency and improves model accuracy by up to 40%.

Due to the powerful representation ability and superior performance of Deep Neural Networks (DNN), Federated Learning (FL) based on DNN has attracted much attention from both academic and industrial fields. However, its transmitted plaintext data causes privacy disclosure. FL based on Local Differential Privacy (LDP) solutions can provide privacy protection to a certain extent, but these solutions still cannot achieve adaptive perturbation in DNN model. In addition, this kind of schemes cause high communication overheads due to the curse of dimensionality of DNN, and are naturally vulnerable to backdoor attacks due to the inherent distributed characteristic. To solve these issues, we propose anEfficient andSecureFederatedLearning scheme (ESFL) against backdoor attacks by using adaptive LDP and compressive sensing. Formal security analysis proves that ESFL satisfies$\epsilon$-LDP security. Extensive experiments using three datasets demonstrate that ESFL can solve the problems of traditional LDP-based FL schemes without a loss of model accuracy and efficiently resist the backdoor attacks.

Federated learning (FL) was once considered secure for keeping clients’ raw data locally without relaying on a central server. However, the transmitted model weights or gradients still reveal private information, which can be exploited to launch various inference attacks. Moreover, FL based on deep neural networks is prone to the curse of dimensionality. In this paper, we propose a compressed and privacy-preserving FL scheme in DNN architecture by using Compressive sensing and Adaptive local differential privacy (called as CAFL). Specifically, we first compress the local models by using Compressive Sensing (CS), then adaptively perturb the remaining weights according to their different centers of variation ranges in different layers and their own offsets from corresponding range centers by using Local Differential Privacy (LDP), finally reconstruct the global model almost perfectly by using the reconstruction algorithm of CS. Formal security analysis shows that our scheme achieves ϵ-LDP security and introduces zero bias to estimating average weights. Extensive experiments using MINIST and Fashion-MINIST datasets demonstrate that our scheme with minimum compression ratio 0.05 can reduce the number of parameters by 95%, and with a lower privacy budget ϵ = 1 can improve the accuracy by 80% on MINIST and 12.7% on Fashion-MINIST compared with state-of-the-art schemes.