FedDAD: Solving the Islanding Problem of SAR Image Aircraft Detection Data

Jia, Zhiwei; Zheng, Haoliang; Wang, Rongjie; Zhou, Wu‐Xing

doi:10.3390/rs15143620

Cited by 6 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Geyer et al [65] first applied DP under Gaussian Mechanism to federated learning to preserve clients' level privacy. While they only achieved 78%,92%, and 96% accuracy with ( , m, n) = (8, 11, 100), (8,54,1000), (8,12,10, 000) on MNIST with differential privacy, where ( , m, n) represented the privacy budget, communication rounds, and clients number, respectively. LDP was first exploited for federated learning by Bhowmick et al [66].…”

Section: Performance Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

Local Differential Privacy Based Membership-Privacy-Preserving Federated Learning for Deep-Learning-Driven Remote Sensing

Zhang,

Ma,

2023

Remote Sensing

View full text Add to dashboard Cite

With the development of deep learning, image recognition based on deep learning is now widely used in remote sensing. As we know, the effectiveness of deep learning models significantly benefits from the size and quality of the dataset. However, remote sensing data are often distributed in different parts. They cannot be shared directly for privacy and security reasons, and this has motivated some scholars to apply federated learning (FL) to remote sensing. However, research has found that federated learning is usually vulnerable to white-box membership inference attacks (MIAs), which aim to infer whether a piece of data was participating in model training. In remote sensing, the MIA can lead to the disclosure of sensitive information about the model trainers, such as their location and type, as well as time information about the remote sensing equipment. To solve this issue, we consider embedding local differential privacy (LDP) into FL and propose LDP-Fed. LDP-Fed performs local differential privacy perturbation after properly pruning the uploaded parameters, preventing the central server from obtaining the original local models from the participants. To achieve a trade-off between privacy and model performance, LDP-Fed adds different noise levels to the parameters for various layers of the local models. This paper conducted comprehensive experiments to evaluate the framework’s effectiveness on two remote sensing image datasets and two machine learning benchmark datasets. The results demonstrate that remote sensing image classification models are susceptible to MIAs, and our framework can successfully defend against white-box MIA while achieving an excellent global model.

show abstract

Section: Performance Comparisonmentioning

confidence: 99%

“…This is one of the major problems affecting the practical application of deep learning algorithms in remote sensing. To solve this problem, federated learning has been researched and applied to remote sensing [8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Local Differential Privacy Based Membership-Privacy-Preserving Federated Learning for Deep-Learning-Driven Remote Sensing

Zhang,

Ma,

2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…16 Jia et al validated that the proposed federated aggregation algorithm, based on model training quality and label distribution, outperforms FedAvg based on YOLOv5s in terms of accuracy. 17 Considering the constrained hardware configurations at engineering sites, deploying algorithms necessitates specific decreases in weight and speed requirements. Li et al proposed an InsDist method that presents a parameter-free masking module simultaneously constructing the relationship between different instances, obtaining significant gains on both one-and two-level as well as anchored and unanchored based detectors.…”

Section: Introductionmentioning

confidence: 99%

Lightweight target detection algorithm based on partial convolution

Chen,

Liu

2024

J. Electron. Imag.

View full text Add to dashboard Cite

You only look once (YOLO) target detection algorithms have garnered substantial attention in engineering inspection tasks due to their remarkable accuracy and swift detection speed. However, adapting the YOLOv7 algorithm to engineering construction presents challenges in balancing lightweight design and high precision. This work introduces a YOLOv7 lightweight detection algorithm, leveraging partial convolution to efficiently reduce network parameters without compromising detection speed. Integrating partial convolution into the network's backbone is a highly effective parameter reduction strategy. Additionally, we propose the SE_Conv module following quantitative analyses through experiments, thereby significantly enhancing the algorithm's detection accuracy. To address the impact of low-quality data on detection effectiveness in engineering tasks, the advanced bounding box loss function WIoU is employed. In a practical application scenario involving helmet detection, the algorithm achieves a notable 23.4% reduction in parameters and a substantial 28.2% decrease in operations through partial convolution. Subsequent experiments with the SE_Conv module yield a noteworthy 1.4% improvement in results. Significantly, in head detection, our algorithm surpasses YOLOv8 algorithm by 2.6% and single shot multibox detector algorithm by 9.4%. These findings underscore the efficacy of our proposed algorithm in engineering applications.

show abstract