Federated learning (FL), an attractive and promising distributed machine learning paradigm, has sparked extensive interest in exploiting tremendous data stored on ubiquitous mobile devices. However, conventional FL suffers severely from resource heterogeneity, as clients with weak computational and communication capabilities may be unable to complete local training using the same local training hyper-parameters. In this article, we propose Dap-FL, a deep deterministic policy gradient (DDPG)-assisted adaptive FL system, in which local learning rates and local training epochs are adaptively adjusted by all resource-heterogeneous clients through locally deployed DDPG-assisted adaptive hyper-parameter selection schemes. Particularly, the rationality of the proposed hyper-parameter selection scheme is confirmed through rigorous mathematical proof. Besides, due to the thoughtlessness of security consideration of adaptive FL systems in previous studies, we introduce the Paillier cryptosystem to aggregate local models in a secure and privacy-preserving manner. Rigorous analyses show that the proposed Dap-FL system could protect clients’ private local models against chosen-plaintext attacks and chosen-message attacks in a widely used honest-but-curious participants and active adversaries security model. More importantly, through ingenious and extensive experiments, the proposed Dap-FL achieves higher model prediction accuracy than two state-of-the-art RL-assisted FL methods, i.e., 6.03% higher than DDPG-based FL and 7.85% higher than DQN-based FL. In addition, experimental results also show that the proposed Dap-FL achieves higher global model prediction accuracy and faster convergence rates than conventional FL, and the comprehensiveness of the adjusted local training hyper-parameters is validated.

With the deployment of local differential privacy (LDP), federated learning (FL) has gained stronger privacy-preserving capability against inference-type attacks. However, existing LDP methods reduce global model performance. In this paper, we propose a QP-LDP algorithm for FL to obtain a better-performed global model without losing privacy guarantees defined by the original LDP. Different from previous LDP methods for FL, QP-LDP improves the global model performance by precisely disturbing the non-common components of quantized local contributions. In addition, QP-LDP comprehensively protects two types of local contributions. Through security analysis, QP-LDP provides the probability indistinguishability of clients' private local contributions at a component-level. More importantly, ingenious experiments show that with the deployment of QP-LDP, the global model outperforms that in the original LDP-based FL in terms of prediction accuracy and convergence rate.

Federated learning (FL) combined with local differential privacy (LDP) has attracted considerable attention due to its privacy-preserving capability against inference-type attacks, e.g., model inversion attacks and membership inference attacks. However, the noise introduced by LDP reduces the global model performance, while decreasing the noise by setting a larger privacy budget sacrifices the privacy guarantees. In this paper, we propose a layer-wise LDP for the FL system, dubbed LLDP, which disturbs various layers of a local model according to clients’ self-assigned privacy budgets. With the deployment of LLDP, clients could train a highly accurate and rapid-converged global model without loosing privacy guarantees. Through extensive security analyses, the proposed LLDP scheme helps the entire local model achieve (ε,δ)-LDP, and the probability indistinguishability of the local model is achieved under the widespread semi-honest threat model. Ingenious experiments show that LLDP improves the global model prediction and convergence rate by 3.38% and 4.76% on the CIFAR-10 dataset compared to the state-of-the-art LDP method with the same privacy budget. In addition, given the same training target (loss value), LLDP requires a 26.67% lower privacy budget, providing stronger privacy guarantees against model inversion attacks.

Targets detection and segmentation in a synthetic aperture radar (SAR) image is a vital step for its interpretation. It is quite challenging for most conventional methods due to complex background and the speckle. Furthermore, the sizes of targets in a scene are variable. Inspired by the success of neural networks in computer vision, In this paper, we propose a 3D dilated multi-scale U-shape convolutional neural network (3DDM-UNet). In the proposed method, we first build a 3D image block via a multiscale stationary wavelet transform to exploit the structural information of targets with various sizes. Then, the built 3D image block is fed into a 3D dilated multiscale U-Net. To train the proposed network, we build a dataset from a scene of SAR image with various sizes and shapes of ship targets. Finally, the trained network is employed to the testing set to obtain the segmentation results. Experimental results on test images show that the proposed method achieved better performance than conventional methods.

The sparsity of targets intrinsically paves a new way to apply compressive sensing (CS) to inverse SAR (ISAR) imaging. However, in the CS-based ISAR imaging system, the ISAR image is considered as a vector composed of random and independent scattering points, and the dependence between pixels is ignored, which always results in the degradation of the shape and geometry of targets, especially when the number of CS measurements and the signal-to-noise ratio are small. In this letter, a novel ISAR imaging framework is proposed via a combination of local sparsity constraint and nonlocal total variation (NLTV). The sparsity is a form prior that the number of strong scattering points is smaller than that of pixels in the image plane. It plays the role of classification of the strong scattering point from the clutter background. NLTV aims to suppress the noise and to remove some false strong scattering centers or clutter and simultaneously preserves the shape and geometry of target regions. Experiments on real data confirm the proposed method's validity.

In this letter, a robust and fast unsupervised change-detection framework is proposed for synthetic aperture radar (SAR) images. It contains three aspects. First, a robust difference image is constructed with the idea of probability patch-based, and it can suppress the speckle effects on the changed regions and enhance the change information synchronously. Then, each class of the difference image is modeled by generalized Gaussian distribution (GGD), and its parameters are learned by the expectation-maximization algorithm. Moreover, the graph-cut algorithm is employed on the difference image to extract the spatial prior information, based on which the parameters of GGD are initialized well via the fuzzyc-means algorithm. Finally, the Bayesian inference for maximum a posteriori performs the final detection. Experimental results on simulated and real SAR data sets confirm the robustness and accuracy of the proposed algorithm in which graph-cut and GGD make great contribution on improving the accuracy of detection and speed of algorithm.