检索结果-内蒙古大学图书馆

Sparse point spread function-based multi-image optical encryption

COMMUNICATIONS PHYSICS 2025年第1期8卷 1-9页

作者： Xu, Ning Qi, Dalong Cheng, Long Pan, Zhen Zhou, Chengyu Lin, Wenzhang Ma, Hongmei Yao, Yunhua Shen, Yuecheng Deng, Lianzhong Sun, Zhenrong Zhang, Shian East China Normal Univ Sch Phys & Elect Sci State Key Lab Precis Spect Shanghai Peoples R China East China Normal Univ Joint Res Ctr Light Manipulat Sci & Photon Integra Shanghai Peoples R China Shanxi Univ Collaborat Innovat Ctr Extreme Opt Taiyuan Peoples R China

Multi-image optical encryption (MOE) has demonstrated promising potential in image data protection owing to its parallel processing capability and abundant degrees of freedom. However, existing methods suffer from either low compression ratios or stringent experimental conditions, such as accurate calibration of phase modulation, precise manufacturing of encryption elements, and no ambient light interference. This work introduces a lensless sparse point spread function-based multi-image optical encryption (sPSF-MOE) technique that addresses these challenges and enhances performance. In the encryption process, each plaintext image is encoded using a sparsely distributed PSF with specifically designed geometric shapes through spatial phase engineering. The resulting ciphertexts are superimposed to produce a compressed ciphertext. During decryption, an iterative algorithm recovers encrypted images with improved reconstruction quality. We show that sPSF-MOE ensures high fidelity for binary (gray-scale) images at a compression ratio of 12 (6) and resists autocorrelation-based attacks. Integrating principal component analysis (PCA) into decryption preserves image high fidelity under ambient light interference. sPSF-MOE reduces the bandwidth requirement for data transmission while ensuring data integrity.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Disttack: Graph Adversarial Attacks Toward distributed GNN Training 30th

Disttack: Graph Adversarial Attacks Toward Distributed GNN T...

引用

30th European Conference on parallel and distributed processing (Euro-Par)

作者： Zhang, Yuxiang Liu, Xin Wu, Meng Yan, Wei Yan, Mingyu Ye, Xiaochun Fan, Dongrui Chinese Acad Sci Inst Comp Technol SKLP Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Zhongguancun Lab Beijing Peoples R China

ISBN: (纸本)9783031697654;9783031697661

Graph Neural Networks (GNNs) have emerged as potent models for graph learning. Distributing the training process across multiple computing nodes is the most promising solution to address the challenges of ever-growing real-world graphs. However, current adversarial attack methods on GNNs neglect the characteristics and applications of the distributed scenario, leading to suboptimal performance and inefficiency in attacking distributed GNN training. In this study, we introduce Disttack, the first framework of adversarial attacks for distributed GNN training that leverages the characteristics of frequent gradient updates in a distributed system. Specifically, Disttack corrupts distributed GNN training by injecting adversarial attacks into one single computing node. The attacked subgraphs are precisely perturbed to induce an abnormal gradient ascent in backpropagation, disrupting gradient synchronization between computing nodes and thus leading to a significant performance decline of the trained GNN. We evaluate Disttack on four large real-world graphs by attacking five widely adopted GNNs. Compared with the state-of-the-art attack method, experimental results demonstrate that Disttack amplifies the model accuracy degradation by 2.75x and achieves speedup by 17.33x on average while maintaining unnoticeability.

关键词： Graph Neural Network distributed Training Adversarial Attack

来源：评论

学校读者我要写书评

暂无评论

Efficient Allocation of image Recognition and LLM Tasks on Multi-GPU System 15th

Efficient Allocation of Image Recognition and LLM Tasks on...

引用

15th International Conference on parallel processing and Applied Mathematics, PPAM 2024

作者： Lawenda, Marcin Samborski, Krzesimir Khloponin, Kyrylo Szustak, Lukasz Poznan Supercomputing and Networking Center Jana Pawla II 10 Poznań61-139 Poland Czestochowa University of Technology Dąbrowskiego 69 Częstochowa42-201 Poland

ISBN: (纸本)9783031857027

This work is concerned with the evaluation of the performance of parallelization of learning and tuning processes for image classification and large language models. For machine learning model in image recognition, various parallelization methods are developed based on different hardware and software scenarios: simple data parallelism, distributed data parallelism, and distributed processing. A detailed description of presented strategies is given, highlighting the challenges and benefits of their application. Furthermore, the impact of different dataset types on the tuning process of large language models is investigated. Experiments show to what extent the task type affects the iteration time in a multi-GPU environment, offering valuable insights into the optimal data utilization strategies to improve model performance. Furthermore, this study leverages the built-in parallelization mechanisms of PyTorch that can facilitate these tasks. Furthermore, performance profiling is incorporated into the study to thoroughly evaluate the impact of memory and communication operations during the training/tuning procedure. Test scenarios are developed and tested with numerous benchmarks on the NVIDIA H100 architecture showing efficiency through selected metrics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

distributed Real-Time image processing of Formation Flying SAR Based on Embedded GPUs

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 6495-6505页

作者： Yang, Tao Xu, Qingbo Meng, Fanteng Zhang, Shuangxi Xidian Univ Sch Aerosp Sci & Technol Xian 710126 Peoples R China Xidian Univ Natl Lab Radar Signal Proc Xian 710126 Peoples R China Northwestern Polytech Univ Sch Elect & Informat Xian 710071 Peoples R China

Formation flying synthetic aperture radar (FF-SAR) systems, as an important development direction of multichannel SAR, can achieve high-resolution wide-swath imaging. Coherently combining data from satellite receivers puts a strain on the traditional real-time processing systems based on individual satellites. Characteristics, such as the power of real-time on-orbit processing platform, must be properly balanced with constrained memory and parallel computational resources. This article proposes a distributed SAR real-time imaging method based on the embedded graphics processing units (GPUs). The parallel computing method of the chirp scaling algorithm is designed based on the parallel programming model of compute unified device architecture, and the optimization methods of memory and performance are proposed for the hardware architecture of embedded GPUs. In particular, the unified memory management method is used to avoid data copying and communication delays between the CPU and GPU. A hardware verification system for distributed SAR real-time imaging processing based on multiple embedded GPUs is constructed. The proposed algorithm takes 5.86 s to process single-precision floating-point complex imaging with a data size of 8192 x 8192 on a single Jetson Nano platform. The actual power consumption is less than 5 W, and the performance-to-power ratio is greater than 1.7%. The experimental results show that the real-time processing method based on the embedded GPUs proposed in this article has high performance and low-power consumption.

关键词： Graphics processing units Imaging Azimuth Synthetic aperture radar Real-time systems Satellites Radar polarimetry Chirp scaling (CS) algorithm distributed architecture embedded graphics processing unit (GPU) on-orbit real-time processing synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Lightweight Byzantine-Robust and Privacy-Preserving Federated Learning 30th

Lightweight Byzantine-Robust and Privacy-Preserving Federate...

引用

30th European Conference on parallel and distributed processing (Euro-Par)

作者： Lu, Zhi Lu, Songfeng Cui, Yongquan Wu, Junjun Nie, Hewang Xiao, Jue Yi, Zepu Huazhong Univ Sci & Technol Hubei Key Lab Distributed Syst Secur Hubei Engn Res Ctr Big Data Secur Sch Cyber Sci & Engn Wuhan 430074 Peoples R China Shenzhen Huazhong Univ Sci & Technol Res Inst Shenzhen 518063 Peoples R China

ISBN: (纸本)9783031697654;9783031697661

Federated learning (FL) is a distributed machine learning approach that reduces data transfer by aggregating gradients from multiple users. However, this process raises concerns about user privacy, leading to the emergence of privacy preserving FL. Unfortunately, this development poses new Byzantine-robustness challenges as poisoning attacks become difficult to detect. Existing byzantine-robust algorithms operate primarily in plaintext, and crucially, current byzantine-robust privacy FL methods fail to concurrently defend against adaptive attacks. In response, we propose a lightweight, byzantine-robust, and privacy-preserving federated learning framework (LRFL), employing shuffle functions and encryption masks to ensure privacy. In addition, we comprehensively calculate the similarity of the direction and magnitude of each gradient vector to ensure byzantine-robustness. To the best of our knowledge, LRFL is the first byzantine-robust privacy preserving FL capable of identifying malicious users based on gradient angles and magnitudes. What's more, the theoretical complexity of LRFL is O(dN + dN logN), comparable to byzantine-robust FL with user number N and gradient dimension d. Experimental results demonstrate that LRFL achieves similar accuracy to state-of-the-art methods under multiple attack scenarios.

关键词： Federated learning Byzantine robustness Privacy protection distributed machine Learning distributed aggregation

来源：评论

学校读者我要写书评

暂无评论

FCTNet: A CNN-Transformer Hybrid for Single Remote Sensing image Super-Resolution 22

FCTNet: A CNN-Transformer Hybrid for Single Remote Sensing I...

引用

22nd IEEE International Symposium on parallel and distributed processing with Applications, ISPA 2024

作者： Shi, Ning Zhou, Hui Ye, Chunyang Yao, Biyuan Wu, Yilin Li, Bo Hainan University Haikou China

ISBN: (纸本)9798331509712

Convolutional Neural Network (CNN) and Transformer architectures have been extensively applied in the domain of remote sensing image super-resolution. However, to achieve optimal performance, many existing methods are designed with a large number of parameters, thereby increasing the complexity of the model and hindering practical deployment. To address this issue, we propose an innovative model that synergizes CNN and Transformer architectures while employing a minimal number of their respective modules. This approach significantly reduces the parameter count while maintaining superior performance. Firstly, by constructing additional shallow feature representations as input, we enhance the feature extraction capabilities for individual images. Secondly, we utilize residual connections between various modules to integrate multi-scale, high-dimensional feature information, thus ensuring efficient transmission. Finally, the image reconstruction module is employed to restore the high-resolution image. Experimental results show that FCTNet significantly outperforms existing methods while maintaining a substantially lower parameter count, as demonstrated through evaluations on two public datasets. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

High-Precision Encrypted image Retrieval Scheme Using Dual-Stream Convolution Feature Fusion in Cloud Computing 22

High-Precision Encrypted Image Retrieval Scheme Using Dual-S...

引用

22nd IEEE International Symposium on parallel and distributed processing with Applications, ISPA 2024

作者： Li, Mingyue Zheng, Liudong Liu, Jiahui Du, Ruizhong Jia, Chunfu Hebei University Baoding China Nankai University Tianjin China

ISBN: (纸本)9798331509712

The retrieval of encrypted images in cloud computing is a research hotspot at present. However, the existing schemes have the problem of low image retrieval accuracy since it is difficult to obtain accurate feature information through convolutional neural network from encrypted image. In this paper, a secure image retrieval method using dual-stream convolution structure for feature fusion is proposed. Specifically, the stream cryptographic image containing contour features and the Fourier transform image containing frequency domain features are used as the two inputs of the convolutional network stream, where the weighted average gate function helps to integrate the feature information in these streams to achieve a more comprehensive feature representation and improve the retrieval accuracy. Furthermore, to keep the contour features of the encrypted image, the fuzzy image and Arnold mapping algorithm are selected randomly to encrypt the encrypted image twice. Experimental evaluation on three datasets, MNIST, Fashion-MNIST and CIFAR-100, shows that the proposed encryption method has higher security than AES and stream cipher encryption. In addition, the retrieval average accuracy (mAP) of this scheme is superior to the existing methods. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Coded distributed Computation for Resilient Prediction Serving Systems 30th

Asymmetric Coded Distributed Computation for Resilient Predi...

引用

30th European Conference on parallel and distributed processing (Euro-Par)

作者： Wang, Lin Hu, Yuchong Liu, Yuxue Xiao, Renzhi Feng, Dan Huazhong Univ Sci & Technol Wuhan Peoples R China

ISBN: (纸本)9783031697654;9783031697661

With the surge of AI services, prediction serving systems (PSSes) have been widely deployed. PSSes are often run on many workers and thus are prone to stragglers (slowdowns or failures), so it is critical to design straggler-resilient PSSes for low latency of prediction. A traditional way is replication that assigns the same prediction job to multiple workers, while incurring significant resources overheads due to its replicated redundant jobs. Recently, coded distributed computation (CDC) has become a more resource-efficient way than replication, as it encodes the prediction job into parity units for prediction reconstruction via decoding. However, we find that state-of-the-art CDC methods either trade accuracy for low latency with the encoder and decoder both simple, or trade latency for high accuracy with the encoder and decoder both complicated, leading to unbalance between accuracy and latency due to the above symmetry between the encoder and decoder. Our insight is that the encoder is always used in CDC-based prediction, while the decoder is only used when stragglers occur. In this paper, we first propose a new asymmetric CDC framework based on the insight, called AsymCDC, composed of a simple encoder but a complicated decoder, such that the encoder's simplicity makes a low encoding time that reduces the latency largely, while the decoder's complexity can be helpful for accuracy. Further, we design the decoder's complexity in two steps: i) an exact decoding method that leverages an invertible neural network's (INN) invertibility to make the decoding have no accuracy loss, and ii) a decoder compacting method that reshapes INN outputs to utilize knowledge distillation effectively that compacts the decoder for low decoding time. We prototype AsymCDC atop Clipper and experiments show that the prediction accuracy of AsymCDC is approximately the same as state-of-the-arts with the encoder and decoder both complicated, while the latency of AsymCDC only exceeds that of

关键词： Forward error correction

来源：评论

学校读者我要写书评

暂无评论

Multi-scale change monitoring of water environment using cloud computing in optimal resolution remote sensing images

引用

ENERGY REPORTS 2022年 8卷 13610-13620页

作者： Feng, Lei You, Yu Liao, Weiling Pang, Jiawei Hu, Ronghao Feng, Li Chinese Acad Sci Chongqing Inst Green & Intelligent Technol Super Resolut Opt Res Ctr Chongqing 400714 Peoples R China Chongqing Environm & Ecol Big Data Applicat Ctr Chongqing 401121 Peoples R China Chongqing Acad Ecol & Environm Sci Water Environm Engn Technol Innovat Ctr Chongqing 401120 Peoples R China Chongqing Pulusi Environm Protect Technol Dev Co L Chongqing 401121 Peoples R China Chongqing Univ Posts & Telecommun Coll Optoelect Engn Chongqing 400065 Peoples R China

Water is the source of life and a very important part of life. However, the current water resources security is facing global challenges. Affected by climate change and human factors, how to quickly realize the continuous monitoring of water resources changes is crucial to the sustainable management of water resources. In recent years, the amount of multi-temporal remote sensing data has grown rapidly, which has caused problems such as weak single-computer processing for change detection and difficulty in mass image storage management. Traditional single-computer processing methods can no longer meet the needs of remote sensing big data change detection. It provides cutting-edge methods and means for monitoring large-scale changes in water resources. Therefore, a distributed parallel method for remote sensing image change detection based on cloud computing is proposed. Through this method, the change detection efficiency of massive remote sensing images is improved, and the high-resolution remote sensing image change detection based on fully connected conditional random fields is deeply analyzed. By summarizing the experimental data of this method and comparing with other data, it can be seen that when the parallelism is higher, the advantage of running time is more obvious. The performance improvement is also as high as 89.49%. Therefore, distributed parallel processing through cloud computing can complete the efficient change detection of massive remote sensing images without affecting the accuracy. This helps us to better monitor and monitor water resources at multiple scales.

关键词： Cloud computing Remote sensing image Water resource Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Optimization of the Functional Decomposition of parallel and distributed Computations in Graph Coloring With the Use of High-Performance Computing

引用

IEEE ACCESS 2022年 10卷 34996-35011页

作者： Skrinarova, Jarmila Dudas, Adam Matej Bel Univ Fac Nat Sci Dept Comp Sci Banska Bystrica 97401 Slovakia

This article presents methods for correct decomposition for high performance computations related to large sets of graphs. These computations contain large number of calls of sequential, recursive algorithm for NP-complete problem - proper edge coloring of graph. Decomposition of this computational problem is not trivial, since the number of recursions in various parts of the computation is different and causes a high load and time imbalance. We designed, implemented and experimentally verified a new decomposition method that significantly reduces the computational time for a large set of graphs (up to 404 million graphs). This method ensures the same duration of computational time for partial subtasks and thus eliminates the need to wait for synchronization of parallel computations.

关键词： Task analysis parallel processing image color analysis Resource management Program processors NP-complete problem Load management Decomposition distributed computing graph coloring parallel computing snark

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：