Adversarial sample-based privacy protection has its own advantages compared to traditional privacy protections. Previous adversarial sample privacy protections have mostly been centralized or have not considered the issue of hardware device limitations when conducting privacy protection, especially on the user’s local device. This work attempts to reduce the requirements of adversarial sample privacy protections on devices, making the privacy protection more locally friendly. Adversarial sample-based privacy protections rely on deep learning models, which generally have a large number of parameters, posing challenges for deployment. Fortunately, the model structural pruning technique has been proposed, which can be employed to reduce the parameter count of deep learning models. Based on the model pruning technique Depgraph and existing adversarial sample privacy protections AttriGuard and MemGuard, we design two structural pruning-based adversarial sample privacy protections, in which the user obtains the perturbed data through the pruned deep learning model. Extensive experiments are conducted on four datasets, and the results demonstrate the effectiveness of our adversarial sample privacy protection based on structural pruning.
Cloud storage has become prevalent in Internet of Things (IoT) systems, attributed to its robust storage capabilities and user convenience. However, the cloud-based storage model, which separates data ownership from management, introduces integrity challenges due to the vulnerability of data to tampering. To address the risk of data loss and ensure recoverability, the implementation of multiple replicas is a common strategy. Nonetheless, traditional multi-replica auditing schemes are not well-suited for IoT environments that employ lightweight devices with limited computational capabilities. In response to the aforementioned challenges, we propose a novel multi-replica auditing scheme named CCMR, aimed at alleviating the heavy computation cost on the device side. Our scheme leverages an efficient aggregated multi-signature algorithm, offloading computationally intensive tasks associated with data tags from lightweight devices to cloud service providers equipped with advanced computational power. The innovative cross-cloud multi-replica hash tree structure, named CC-MHT, facilitates the secure and efficient verification of data block structures and ensures consistency of replicas across multi-cloud environments. Furthermore, by utilizing blockchain as a public random source, a robust challenge-response protocol is established to guard against potential audit failures that could arise from collusion between the third-party auditor and cloud service providers. The experimental results indicate the high efficiency of the proposed scheme in terms of computation cost.
17 March 2020 in Transactions on Emerging Telecommunications Technologies
In multi-UAV networks with limited ground edge nodes, computational offloading poses significant challenges. The absence of a robust terrestrial network exacerbates these issues. To address this, we propose a framework based on satellite-UAV integrated systems, incorporating LEO satellite constellations. A two-layer UAV architecture is designed to categorize UAVs by function. Our study models communication dynamics and offloading processes, aiming to jointly optimize decisions, ratios, trajectories, and LEO frequency allocation. To tackle high-dimensional complexity and dynamic network conditions, we develop a multi-intelligent body deep deterministic policy gradient algorithm. Each task-generating UAV acts as an agent, adjusting its trajectory and offloading decisions in real-time. Simulations validate our framework, showing significant improvements over baseline approaches in minimizing delay, energy consumption, and computational costs.
The design of conventional digital predistortion (DPD) requires an analogue-to-digital converter (ADC) with a sampling frequency that is multiple times the signal bandwidth, which is extremely challenging for sub-Nyquist sampling systems with undersampled signals. To address this, this paper proposes a neural network (NN)-assisted wideband power amplifier (PA) DPD method for sub-Nyquist sampling systems, wherein a dual-stage architecture is designed to handle the ambiguity caused by subsampled communications signals. In the first stage, the time-delayed polynomial reconstruction method is employed to estimate the wideband DPD nonlinearity coarsely with the undersampled signals with limited pilots. In the second stage, an NN-based DPD method is proposed for the virtual training of the DPD, which learns the up-sampled DPD behavior by taking advantage of the pre-estimated DPD model and the input data signals, which reduces the length of the training sequence significantly and refines the DPD behavior efficiently. Simulation results demonstrate the efficacy of the proposed method in tackling the wideband PA nonlinearity and its ability to outperform the conventional method in terms of power spectrum, error vector magnitude, and bit error rate.
11 February 2025 in IEEE Transactions on Consumer Electronics
With the proliferation of Internet of Things devices, federated Generative Adversarial Networks (GAN) have become an effective tool for handling data deficiencies in distributed architectures. However, in federated learning scenarios, due to the non-independently and identically distributed (non-IID) nature of data, the training of federated GAN faces multiple challenges. Existing works on federated GAN training still face limitations when confronted with highly heterogeneous data. To address these issues, this paper proposes a federated data augmentation and aggregation scheme based on Conditional GAN (CGAN), named TSTFL-CGAN. The method divides federated GAN training into two stages: pre-training and formal training. It uses fuzzy logic to handle uncertain data and allows the global server to flexibly allocate generators to supplement the missing samples on client. Additionally, we introduce a time factor to dynamically adjust each client’s model contribution to global aggregation based on the model training loss and data volume, which accelerates convergence and enhances the performance of the global model. Extensive experiments show that TSTFL-CGAN achieves convergence within 3 rounds of aggregation across 4 different data distribution scenarios, and it demonstrates an improvement of 10 to 30 in the evaluation of generated sample quality.