Privacy preservation is critical for neuralnetwork inference, which often involves collaborative execution of different parties to make predictions on sensitive data based on sensitive neuralnetwork models. However,...
详细信息
In this paper, we describe possible applications of early exit deep neuralnetworks in magnetic resonance imaging, aiming to improve patient scan times and reduce processing costs. The solutions rely on deep neural ne...
详细信息
The proceedings contain 42 papers. The topics discussed include: an efficient compilation of coarse-grained reconfigurable architectures utilizing pre-optimized sub-graph mappings;evaluating micro-batch and data frequ...
ISBN:
(纸本)9781665469586
The proceedings contain 42 papers. The topics discussed include: an efficient compilation of coarse-grained reconfigurable architectures utilizing pre-optimized sub-graph mappings;evaluating micro-batch and data frequency for stream processing applications on multi-cores;a parallel approximation algorithm for the steiner forest problem;exploiting vector extensions to accelerate time series analysis;a neuralnetwork to estimate isolated performance from multi-program execution;a heuristic for constructing minimum average stretch spanning tree using betweenness centrality;accelerating distributed deep reinforcement learning by in-network experience sampling;parallel integer multiplication;advancing database system operators with near-data processing;and clustering datasets in cloud computing environment for user identification.
Privacy preservation is critical for neuralnetwork inference, which often involves collaborative execution of different parties to make predictions on sensitive data based on sensitive neuralnetwork models. However,...
详细信息
ISBN:
(数字)9798350317152
ISBN:
(纸本)9798350317169
Privacy preservation is critical for neuralnetwork inference, which often involves collaborative execution of different parties to make predictions on sensitive data based on sensitive neuralnetwork models. However, the expensive cryptographic operations of privacy preservation also pose performance chal-lenges to neuralnetwork inference. We address this performance-security tension by designing PP-Stream, a distributed stream processing system for high-performance privacy-preserving neuralnetwork inference. PP-Stream adopts hybrid privacy-preserving mechanisms for linear and non-linear operations of neuralnetwork inference. It treats inference data as real-time data streams, and parallelizes the inference operations across multiple pipelined stages that are executed by multiple servers and threads. It also solves the load-balanced resource allocation across servers and threads as an optimization problem. We prototype PP-Stream and show via testbed experiments that it achieves low inference latencies on various neuralnetwork models.
At present, the commonly used active and passive islanding detection methods have their own shortcomings, and the islanding detection effect is difficult to meet the requirements. Therefore, a new detection method bas...
详细信息
At present, the commonly used active and passive islanding detection methods have their own shortcomings, and the islanding detection effect is difficult to meet the requirements. Therefore, a new detection method based on wavelet signal processing and artificial intelligence to identify islanding is proposed in this paper. In this method, the feature quantities required for islanding detection are obtained by wavelet transform and signal processing, and then the feature quantities are identified by neuralnetwork to determine whether the islanding is generated in distributed generation *** transformation has a strong ability of signal feature extraction, while the neuralnetwork has strong learning and identification abilities, the combination of the both is beneficial to improve the success rate of islanding detection. Simulation verification shows that the new islanding detection method proposed in this paper can detect islanding quickly and accurately, and the performance of islanding detection has been significantly improved.
We consider the problem of routing network packets in a large-scale communication system where the nodes have access to only local information. We formulate this problem as a constrained learning problem, which can be...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
We consider the problem of routing network packets in a large-scale communication system where the nodes have access to only local information. We formulate this problem as a constrained learning problem, which can be solved using a distributed optimization algorithm. We approach this distributed optimization using a novel state-augmentation (SA) strategy to maximize the aggregate information packets at different source nodes, leveraging dual variables corresponding to flow constraint violations. The construction is based on graph neuralnetworks (GNNs) that employ graph convolutions over the underlying communication network topology. We devise an unsupervised learning algorithm to transform the output of the GNN architecture into optimal routing decisions. The proposed method takes advantage of only the local information available at each node and efficiently routes the desired packets to the destination. We provide numerical results demonstrating the superiority of the proposed method over baseline routing algorithms.
The detection of distributed Denial of Service (DDoS) attacks is a critical challenge in network security, requiring effective and efficient solutions to safeguard data and services. This paper addresses this problem ...
详细信息
ISBN:
(纸本)9798350377774;9798350377767
The detection of distributed Denial of Service (DDoS) attacks is a critical challenge in network security, requiring effective and efficient solutions to safeguard data and services. This paper addresses this problem by introducing a neuralnetwork model specifically designed for DDoS attack detection. The model employs a streamlined architecture to ensure rapid processing times and high performance. A key innovation is the integration of Gaussian noise, which enhances the robustness and generalization capabilities of the model. Extensive experiments validate the effectiveness and resilience of this approach, demonstrating its practicality for real-world network security applications. The findings highlight the significant role of noise regularization in improving the reliability of neuralnetwork models for detecting cyber threats.
With advancements in distributed communications for the IoV, security threats expose significant challenges. While current IoV intrusion detection systems demonstrate high accuracy, they rely heavily on private or eas...
详细信息
ISBN:
(纸本)9798350359329;9798350359312
With advancements in distributed communications for the IoV, security threats expose significant challenges. While current IoV intrusion detection systems demonstrate high accuracy, they rely heavily on private or easily forged data. Moreover, the training process incurs increased network communication costs, fails to protect user privacy, and distorted data degrades detection performance. To address these limitations, we proposes a distributed federated learning-based intrusion detection model for IoV using non-private behavior features. Firstly, we design a data processing algorithm that groups and slices IoV communication messages into time series. Then, behavior vectors are extracted using an attention-based time series model designed in this work. Attacks are detected by spatially transforming the residuals with a neuralnetwork. Finally, we use a federated learning algorithm for data processing and training of the model, effectively reduce communication burden and protect privacy training data on the vehicle-side. Extensive experiments on two datasets validate the proposed model, achieving F1 scores of 91.66% and 90.25% respectively, outperforming state-of-theart methods. We publicly release the model and algorithms to improve reproducibility and accessibility of effective IoV intrusion detection solutions.
Growing dataset and model sizes for Deep neuralnetworks (DNNs) training have necessitated distributed training. Despite a rich literature on designing better distributed training algorithms and frameworks, few of the...
详细信息
ISBN:
(纸本)9798400716607
Growing dataset and model sizes for Deep neuralnetworks (DNNs) training have necessitated distributed training. Despite a rich literature on designing better distributed training algorithms and frameworks, few of them touch the lower layers (e.g. transport layer) of TCP/IP model. There's a recent paper [11] calling for rethinking the transport layer for distributed training, which suggests by simulation the potential performance gain from redesigning a new transport layer. Building on this premise, our research identifies TCP's limitations for distributed ML in data centers and introduces a Parameter Server (PS) system with a bounded-loss communication layer. It validates gradient-loss-tolerant neuralnetworks for ML tasks and enhances distributed training efficiency through a novel communication protocol. Preliminary results show that such a method could potentially improve the performance by 8.2X, reinforcing the feasibility of scalable and efficient distributed ML systems.
We present a novel approach to Near-field Acoustic Holography (NAH) with the introduction of the Complex-Valued Kirchhoff-Helmholtz Convolutional neuralnetwork (CV-KHCNN). Our study focuses on analyzing Complex-Value...
详细信息
ISBN:
(纸本)9789464593617;9798331519773
We present a novel approach to Near-field Acoustic Holography (NAH) with the introduction of the Complex-Valued Kirchhoff-Helmholtz Convolutional neuralnetwork (CV-KHCNN). Our study focuses on analyzing Complex-Valued neuralnetworks (CVNNs) in the application of NAH scenario. We compare the performance between CV-KHCNN and its equivalent Real-Valued neuralnetworks (RVNNs). Moreover, different complex activation functions are evaluated for CV-KHCNN. The results emphasize the effectiveness of CVNNs in tackling NAH challenges and highlight the suitability of Cardioid as the activation function for CVNNs. This discovery underscores the promising contributions of CVNNs to the field of NAH. T-distributed Stochastic Neighbor Embedding (t-SNE) is further adopted to visualize the features of the embedding layer. The results show that even without prior knowledge of the vibrations, CV-KHCNN demonstrates the capability to distinguish between different boundary conditions (BCs) and mode shapes.
暂无评论