distributed Machine Learning (DML) methods are expected to play a crucial role in the forthcoming 6G era, with the goal of enabling ubiquitous connected intelligence. distributed intelligence enabled through distribut...
详细信息
ISBN:
(纸本)9798350303582;9798350303599
distributed Machine Learning (DML) methods are expected to play a crucial role in the forthcoming 6G era, with the goal of enabling ubiquitous connected intelligence. distributed intelligence enabled through distributed computing environments, 6G technology, and big data can be extremely supportive of achieving the goals of emerging intelligent IoT applications in the proximity of end users. With this in mind, we propose an advanced Federated Learning (FL) approach for efficiently enabling intelligent applications over latency-critical networks in Non-Terrestrial environments. In the proposed solution, the client and server nodes reduce idle time using a parallelprocessing approach with the help of a replica of the training model. Next, the proposed FL framework is tested in a Python environment to show its effectiveness with respect to the traditional FL approach.
distributed arithmetic (DA) implementation for finite impulse response (FIR) filters on field-programmable gate arrays (FPGAs) is highly desirable in digital signal processing due to its fast computational speed and l...
详细信息
ISBN:
(纸本)9798350340570
distributed arithmetic (DA) implementation for finite impulse response (FIR) filters on field-programmable gate arrays (FPGAs) is highly desirable in digital signal processing due to its fast computational speed and low power consumption. However, traditional LUT-based DA implementation on FPGAs is challenging because of its high memory space requirements. To overcome this challenge, LUT-partition and MUX-incorporation techniques have been proposed to reduce memory space, but they also increase the FPGA resource utilization. Furthermore, the inherent serial nature of DA computing can limit data throughput. parallelprocessing of multiple bits can improve computational performance but at the cost of chip area. Therefore, it is beneficial to combine optimization methods to achieve desired performance. This paper proposes a comprehensive approach for optimizing memory space, computational performance, and chip area by analyzing different LUT partitions and incorporating MUX configurations. The proposed method is evaluated on a Xilinx Zynq 7010 FPGA, demonstrating its effectiveness.
The proceedings contain 131 papers. The special focus in this conference is on Algorithms and Architectures for parallelprocessing. The topics include: MARO: Enabling Full MPI Automatic Refactoring in DSL-Based ...
ISBN:
(纸本)9789819615278
The proceedings contain 131 papers. The special focus in this conference is on Algorithms and Architectures for parallelprocessing. The topics include: MARO: Enabling Full MPI Automatic Refactoring in DSL-Based Programming Framework;SSC: An SRAM-Based Silence Computing Design for On-chip Memory;TP-BFT: A Faster Asynchronous BFT Consensus with parallel Structure;LTP: A Lightweight On-Chip Temporary Prefetcher for Data-Dependent Memory Accesses;A Neural Network-Based PUF Protection Method Against Machine Learning Attack;Compression Format and Systolic Array Structure Co-design for Accelerating Sparse Matrix Multiplication in DNNs;multidimensional Intrinsic Identity Construction and Dynamic Seamless Authentication Schemes in IoT Environments;invisible Backdoor Attack with image Contours Triggers;finestra: Multi-aggregator Swarm Learning for Gradient Leakage Defense;DIsFU: Protecting Innocent Clients in Federated Unlearning;multiple-Round Aggregation of Abstract Semantics for Secure Heterogeneous Federated Learning;dynamic Privacy Protection with Large Language Model in Social Networks;a Dynamic Symmetric Searchable Encryption Scheme for Rapid Conjunctive Queries;a Data Watermark Scheme Base on Data Converted Bitmap for Data Trading;distributed Incentive Algorithm for Fine-Grained Offloading in Vehicular Ad Hoc Networks;mitigating Over-Unlearning in Machine Unlearning with Synthetic Data Augmentation;AW-YOLOv9: Adverse Weather Conditions Adaptation for UAV Detection;efficient and Privacy-Preserving Ranking-Based Federated Learning;on-Chain Dynamic Policy Evaluation for Decentralized Access Control;DPG-FairFL: A Dual-Phase GAN-Based Defense Framework Against image-Based Fairness Data Poisoning Attacks in Federated Learning.
The proceedings contain 131 papers. The special focus in this conference is on Algorithms and Architectures for parallelprocessing. The topics include: MARO: Enabling Full MPI Automatic Refactoring in DSL-Based ...
ISBN:
(纸本)9789819615476
The proceedings contain 131 papers. The special focus in this conference is on Algorithms and Architectures for parallelprocessing. The topics include: MARO: Enabling Full MPI Automatic Refactoring in DSL-Based Programming Framework;SSC: An SRAM-Based Silence Computing Design for On-chip Memory;TP-BFT: A Faster Asynchronous BFT Consensus with parallel Structure;LTP: A Lightweight On-Chip Temporary Prefetcher for Data-Dependent Memory Accesses;A Neural Network-Based PUF Protection Method Against Machine Learning Attack;Compression Format and Systolic Array Structure Co-design for Accelerating Sparse Matrix Multiplication in DNNs;multidimensional Intrinsic Identity Construction and Dynamic Seamless Authentication Schemes in IoT Environments;invisible Backdoor Attack with image Contours Triggers;finestra: Multi-aggregator Swarm Learning for Gradient Leakage Defense;DIsFU: Protecting Innocent Clients in Federated Unlearning;multiple-Round Aggregation of Abstract Semantics for Secure Heterogeneous Federated Learning;dynamic Privacy Protection with Large Language Model in Social Networks;a Dynamic Symmetric Searchable Encryption Scheme for Rapid Conjunctive Queries;a Data Watermark Scheme Base on Data Converted Bitmap for Data Trading;distributed Incentive Algorithm for Fine-Grained Offloading in Vehicular Ad Hoc Networks;mitigating Over-Unlearning in Machine Unlearning with Synthetic Data Augmentation;AW-YOLOv9: Adverse Weather Conditions Adaptation for UAV Detection;efficient and Privacy-Preserving Ranking-Based Federated Learning;on-Chain Dynamic Policy Evaluation for Decentralized Access Control;DPG-FairFL: A Dual-Phase GAN-Based Defense Framework Against image-Based Fairness Data Poisoning Attacks in Federated Learning.
The proceedings contain 131 papers. The special focus in this conference is on Algorithms and Architectures for parallelprocessing. The topics include: MARO: Enabling Full MPI Automatic Refactoring in DSL-Based ...
ISBN:
(纸本)9789819615247
The proceedings contain 131 papers. The special focus in this conference is on Algorithms and Architectures for parallelprocessing. The topics include: MARO: Enabling Full MPI Automatic Refactoring in DSL-Based Programming Framework;SSC: An SRAM-Based Silence Computing Design for On-chip Memory;TP-BFT: A Faster Asynchronous BFT Consensus with parallel Structure;LTP: A Lightweight On-Chip Temporary Prefetcher for Data-Dependent Memory Accesses;A Neural Network-Based PUF Protection Method Against Machine Learning Attack;Compression Format and Systolic Array Structure Co-design for Accelerating Sparse Matrix Multiplication in DNNs;multidimensional Intrinsic Identity Construction and Dynamic Seamless Authentication Schemes in IoT Environments;invisible Backdoor Attack with image Contours Triggers;finestra: Multi-aggregator Swarm Learning for Gradient Leakage Defense;DIsFU: Protecting Innocent Clients in Federated Unlearning;multiple-Round Aggregation of Abstract Semantics for Secure Heterogeneous Federated Learning;dynamic Privacy Protection with Large Language Model in Social Networks;a Dynamic Symmetric Searchable Encryption Scheme for Rapid Conjunctive Queries;a Data Watermark Scheme Base on Data Converted Bitmap for Data Trading;distributed Incentive Algorithm for Fine-Grained Offloading in Vehicular Ad Hoc Networks;mitigating Over-Unlearning in Machine Unlearning with Synthetic Data Augmentation;AW-YOLOv9: Adverse Weather Conditions Adaptation for UAV Detection;efficient and Privacy-Preserving Ranking-Based Federated Learning;on-Chain Dynamic Policy Evaluation for Decentralized Access Control;DPG-FairFL: A Dual-Phase GAN-Based Defense Framework Against image-Based Fairness Data Poisoning Attacks in Federated Learning.
The proceedings contain 131 papers. The special focus in this conference is on Algorithms and Architectures for parallelprocessing. The topics include: MARO: Enabling Full MPI Automatic Refactoring in DSL-Based ...
ISBN:
(纸本)9789819615506
The proceedings contain 131 papers. The special focus in this conference is on Algorithms and Architectures for parallelprocessing. The topics include: MARO: Enabling Full MPI Automatic Refactoring in DSL-Based Programming Framework;SSC: An SRAM-Based Silence Computing Design for On-chip Memory;TP-BFT: A Faster Asynchronous BFT Consensus with parallel Structure;LTP: A Lightweight On-Chip Temporary Prefetcher for Data-Dependent Memory Accesses;A Neural Network-Based PUF Protection Method Against Machine Learning Attack;Compression Format and Systolic Array Structure Co-design for Accelerating Sparse Matrix Multiplication in DNNs;multidimensional Intrinsic Identity Construction and Dynamic Seamless Authentication Schemes in IoT Environments;invisible Backdoor Attack with image Contours Triggers;finestra: Multi-aggregator Swarm Learning for Gradient Leakage Defense;DIsFU: Protecting Innocent Clients in Federated Unlearning;multiple-Round Aggregation of Abstract Semantics for Secure Heterogeneous Federated Learning;dynamic Privacy Protection with Large Language Model in Social Networks;a Dynamic Symmetric Searchable Encryption Scheme for Rapid Conjunctive Queries;a Data Watermark Scheme Base on Data Converted Bitmap for Data Trading;distributed Incentive Algorithm for Fine-Grained Offloading in Vehicular Ad Hoc Networks;mitigating Over-Unlearning in Machine Unlearning with Synthetic Data Augmentation;AW-YOLOv9: Adverse Weather Conditions Adaptation for UAV Detection;efficient and Privacy-Preserving Ranking-Based Federated Learning;on-Chain Dynamic Policy Evaluation for Decentralized Access Control;DPG-FairFL: A Dual-Phase GAN-Based Defense Framework Against image-Based Fairness Data Poisoning Attacks in Federated Learning.
The proceedings contain 131 papers. The special focus in this conference is on Algorithms and Architectures for parallelprocessing. The topics include: MARO: Enabling Full MPI Automatic Refactoring in DSL-Based ...
ISBN:
(纸本)9789819615414
The proceedings contain 131 papers. The special focus in this conference is on Algorithms and Architectures for parallelprocessing. The topics include: MARO: Enabling Full MPI Automatic Refactoring in DSL-Based Programming Framework;SSC: An SRAM-Based Silence Computing Design for On-chip Memory;TP-BFT: A Faster Asynchronous BFT Consensus with parallel Structure;LTP: A Lightweight On-Chip Temporary Prefetcher for Data-Dependent Memory Accesses;A Neural Network-Based PUF Protection Method Against Machine Learning Attack;Compression Format and Systolic Array Structure Co-design for Accelerating Sparse Matrix Multiplication in DNNs;multidimensional Intrinsic Identity Construction and Dynamic Seamless Authentication Schemes in IoT Environments;invisible Backdoor Attack with image Contours Triggers;finestra: Multi-aggregator Swarm Learning for Gradient Leakage Defense;DIsFU: Protecting Innocent Clients in Federated Unlearning;multiple-Round Aggregation of Abstract Semantics for Secure Heterogeneous Federated Learning;dynamic Privacy Protection with Large Language Model in Social Networks;a Dynamic Symmetric Searchable Encryption Scheme for Rapid Conjunctive Queries;a Data Watermark Scheme Base on Data Converted Bitmap for Data Trading;distributed Incentive Algorithm for Fine-Grained Offloading in Vehicular Ad Hoc Networks;mitigating Over-Unlearning in Machine Unlearning with Synthetic Data Augmentation;AW-YOLOv9: Adverse Weather Conditions Adaptation for UAV Detection;efficient and Privacy-Preserving Ranking-Based Federated Learning;on-Chain Dynamic Policy Evaluation for Decentralized Access Control;DPG-FairFL: A Dual-Phase GAN-Based Defense Framework Against image-Based Fairness Data Poisoning Attacks in Federated Learning.
Mobile edge devices require real-time dehazing methods that sustain dehazing performance while drastically reducing resource occupation. However, color distortion is a substantial challenge for lightweight dehazing ne...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
Mobile edge devices require real-time dehazing methods that sustain dehazing performance while drastically reducing resource occupation. However, color distortion is a substantial challenge for lightweight dehazing networks, which profoundly impairs image quality. In this paper, we propose CDCNet, a fast and lightweight dehazing network with color distortion correction, to tackle these challenges. Firstly, CDCNet utilizes a multi-scale feature aggregation module to retain lightweight and leverages a parallel attention module to expedite the dehazing process. Secondly, we devise proportional residual connection and loss functions to mitigate potential color distortion in CDCNet. Thirdly, we design a post-processing module to adjust HSV and Lab color spaces to eliminate color distortions comprehensively. Experiments demonstrate that CDCNet surpasses state-of-the-art lightweight dehazing methods and exhibits superiority in execution time.
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 emer...
详细信息
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.
Genetic algorithms have been widely used in intelligent test paper generation systems. However, traditional genetic algorithms cannot ensure that the difficulty of test questions is normally distributed, and are prone...
详细信息
暂无评论