Autonomous driving systems require real-time environmental perception to ensure user safety and experience. Streaming perception is a task of reporting the current state of the world, which is used to evaluate the del...
详细信息
Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversar...
Isolation forest (iForest) has been emerging as arguably the most popular anomaly detector in recent years due to its general effectiveness across different benchmarks and strong scalability. Nevertheless, its linear ...
详细信息
With the increasing adoption of graph neural networks (GNNs) in the graph-based deep learning community, various graph programming frameworks and models have been developed to improve the productivity of GNNs. The cur...
详细信息
ISBN:
(纸本)9781665443326
With the increasing adoption of graph neural networks (GNNs) in the graph-based deep learning community, various graph programming frameworks and models have been developed to improve the productivity of GNNs. The current GNN frameworks choose GPU as an essential tool to accelerate GNN training. However, it is still challenging to train GNNs on large graphs with limited GPU memory. Unlike traditional neural networks, generating mini-batch data by sampling in GNNs requires some complicated tasks such as traversing the graph to select neighboring nodes and gathering their features. This process takes up most of the training and we find the main bottleneck comes from transferring nodes features from CPU to GPU through limited bandwidth. In this paper, We propose a method Reusing Batch Data for the problem of data transmission. This method utilizes the similarity between adjacent mini-batches to reduce repeated data transmission from CPU to GPU. Furthermore, to reduce the overhead introduced by this method, we design a fast algorithm based on GPU to detect repeated nodes’ data and achieve shorter additional computation time. Evaluations on three representative GNN models show that our method can reduce transmission time by up to 60% and speed the end-to-end GNN training by up to 1.79× over the state-ofthe-art baselines. Besides, Reusing Batch Data can effectively save GPU memory footprint by about 19% to 40% while still reducing the training time compared to the static cache strategy.
In response to the substantial threat that Internet attacks pose to data center network security, researchers have proposed several deep learning-based methods for detecting network intrusions. However, while algorith...
详细信息
ISBN:
(数字)9798350385557
ISBN:
(纸本)9798350385564
In response to the substantial threat that Internet attacks pose to data center network security, researchers have proposed several deep learning-based methods for detecting network intrusions. However, while algorithms are constantly improving in terms of accuracy, their stability in the face of insufficient attack samples is a major obstacle. To solve the issues of insufficient attack samples and low detection accuracy in network intrusion detection, this paper proposes a deep confidence network intrusion detection method G-DBN based on GAN. The model is based on the malicious sample extension of the generative adversarial network, and it can produce adversarial samples using malicious network flows as original samples. Furthermore, this paper uses deep belief network technology to create and assess the efficacy of the G-DBN model in detecting network attacks, comparing it to standard DBN models and other network intrusion detection techniques. Experimental results show that compared to the standard three-layer DBN method, the G-DBN method described in this paper improves the detection accuracy of attack samples by 6.46% and better meets the performance requirements of current practical applications.
There are often dense objects in the images processed by instance segmentation, but too dense objects will cause the problem that the objects are difficult to segment. Most of the current dense instance segmentation m...
详细信息
The pre-training language model BERT has brought significant performance improvements to a series of natural language processing tasks, but due to the large scale of the model, it is difficult to be applied in many pr...
The pre-training language model BERT has brought significant performance improvements to a series of natural language processing tasks, but due to the large scale of the model, it is difficult to be applied in many practical application scenarios. With the continuous development of edge computing, deploying the models on resource-constrained edge devices has become a trend. Considering the distributed edge environment, how to take into account issues such as data distribution differences, labeling costs, and privacy while the model is shrinking is a critical task. The paper proposes a new BERT distillation method with source-free unsupervised domain adaptation. By combining source-free unsupervised domain adaptation and knowledge distillation for optimization and improvement, the performance of the BERT model is improved in the case of cross-domain data. Compared with other methods, our method can improve the average prediction accuracy by up to around 4% through the experimental evaluation of the cross-domain sentiment analysis task.
Among the plethora of IoT(Internet of Things)applications,the smart home is one of the ***,the rapid development of the smart home has also made smart home systems a target for ***,researchers have made many efforts t...
详细信息
Among the plethora of IoT(Internet of Things)applications,the smart home is one of the ***,the rapid development of the smart home has also made smart home systems a target for ***,researchers have made many efforts to investigate and enhance the security of smart home *** a more secure smart home ecosystem,we present a detailed literature review on the security of smart home ***,we categorize smart home systems’security issues into the platform,device,and communication *** exploring the research and specific issues in each of these security areas,we summarize the root causes of the security flaws in today's smart home systems,which include the heterogeneity of internal components of the systems,vendors'customization,the lack of clear responsibility boundaries and the absence of standard security ***,to better understand the security of smart home systems and potentially provide better protection for smart home systems,we propose research directions,including automated vulnerability mining,vigorous security checking,and data-driven security analysis.
A large number of reads generated by the next generation sequencing platform will contain many repetitive subsequences. Effective localizing and identifying genomic regions containing repetitive subsequences will cont...
详细信息
ISBN:
(纸本)9781665496407
A large number of reads generated by the next generation sequencing platform will contain many repetitive subsequences. Effective localizing and identifying genomic regions containing repetitive subsequences will contribute to the subsequent genomic data analysis. To accelerate the alignment between large-scale short reads and reference genome with many repetitive subsequences, this paper develops a compact de Bruijn graph based short-read alignment algorithm on distributedparallelcomputing platform. The algorithm uses resilient distributed data sets (RDDS) to perform calculations in memory, and executes the broadcast method to distribute short reads and reference genome to the computing nodes to reduce the data communication time on the cluster system, and the number of RDD partitions is set to optimize the performance of parallel aligning algorithm. Experimental results on real datasets show that compared with the compact de Bruijn graph based sequential short-read alignment algorithm, our implemented distributedparallel alignment algorithm achieves good acceleration on the premise of obtaining the same correct alignment percentage as a whole, and compared with existing distributedparallel alignment algorithms, the implemented parallel algorithm can more quickly complete the alignment between large-scale short reads and reference genome with highly repetitive subsequences.
作者:
Wang, HongfeiWan, CaixueJin, HaiHuazhong University of Science and Technology
National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China Huazhong University of Science and Technology
National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China
The Physical Unclonable Function (PUF) is valued for its lightweight nature and unique functionality, making it a common choice for securing hardware products requiring authentication and key generation mechanisms. In...
详细信息
暂无评论