检索结果-内蒙古大学图书馆

6th International Symposium on computer and Information Processing Technology, ISCIPT 2021

作者： Zhang, Bofeng Han, Li Sun, Shimin Tianjin University of Technology School of Computer Science and Engineering Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin China Tiangong University Tianjin Key Laboratory of Autonomous Intelligent Technology and System School of Computer Science and Technology Tianjin China

ISBN: (纸本)9781665441377

Moving Target Defense (MTD) is commonly used in changing the asymmetric situation between attack and defense in cyberspace. Route mutation is a vital branch of MTD. Current route mutation methods still have some limitations on unpredictability of mutating routing paths and time overhead. In this paper, we propose a Dynamic Random Route Mutation (DRRM) mechanism in order to maximize the unpredictability of mutation and reduce the time overhead. First, we adopt Jaccard distance matrix and temporal constraint to improve mutation space. Mutation space can be dynamically shifted to enhance the unpredictability. Then, we weaken attackers' capabilities of launching effective eavesdropping at a certain node by using route weight. Finally, we construct a pre-distribution strategy to reduce the transmission latency caused by route mutation. Simulation results show that DRRM not only raises the difficulty of network eavesdropping, but also ensures low mutation time overhead. © 2021 IEEE.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Conformer-Based Speech Recognition Model for Mandarin Radiotelephony Communications in Civil Aviation 16th

An End-to-End Conformer-Based Speech Recognition Model for M...

引用

16th Chinese Conference on Biometric Recognition, CCBR 2022

作者： Shi, Yihua Ma, Guanglin Ren, Jin Zhang, Haigang Yang, Jinfeng Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic Shenzhen518055 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

ISBN: (纸本)9783031202322

In civil aviation radiotelephony communications, misunderstandings between air traffic controllers and flight crews can result in serious aviation accidents. Automatic semantic verification is a promising assistant solution to decrease miscommunication, thanks to advancements in speech and language processing. Unfortunately, existing general speech recognition models are ineffective when it comes to capturing contextual long-distance dependent local similarity features in radiotelephony communications. To address these problems, this paper proposes an end-to-end Conformer-based multi-task learning speech recognition model for Mandarin radiotelephony communications in civil aviation. The Conformer model improves local information capture while retaining the global information modeling capabilities of contextual long-distance dependencies, owing to the introduction of the convolution module to the Transformer model. Meanwhile, multi-task learning is used to further improve performance by combining connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models. The experimental results show that the proposed model can perform global and local acoustic modeling effectively, making it particularly suitable for extracting acoustic features of Mandarin civil aviation radiotelephony communications. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Radio telephone

来源：评论

学校读者我要写书评

暂无评论

Digital Twin and DRL-Driven Semantic Dissemination for 6G Autonomous Driving Service

Digital Twin and DRL-Driven Semantic Dissemination for 6G Au...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Yihang Tao Jun Wu Xi Lin Shahid Mumtaz Soumaya Cherkaoui School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Faculty of Science and Engineering Waseda University Japan Department of Engineering Nottingham Trent University UK Department of Computer and Software Engineering Polytechnique Montreal Canada

Data dissemination is critical for 6G autonomous driving (AD) service because of the extensive demand for real-time traffic information. However, the heavier data transmission burden and more stringent requirements of AD service bring challenges for current data dissemination methods. In this paper, we first propose a novel digital twin (DT)-based semantic dissemination architecture to better support 6G AD service. Under this architecture, an energy-efficient semantic communication mechanism is developed to reduce the data dissemination burden while keeping low semantic model update costs. Meanwhile, the DT network is leveraged to disseminate semantic data in parallel with the physical vehicular networks, which alleviates the physical transmission contention and improves the dissemination efficiency. Second, we design a deep-reinforcement-learning (DRL)-driven semantic data dissemination scheme for the proposed architecture, named Proximal-policy-optimization for Digital-twin-aided Data Dissemination (PD3), which seeks the optimal DT transfer and semantic transmission scheduling strategy. Finally, experimental results show that our approach surpasses the state-of-the-art methods by 18.36% lower dissemination delay and 4.51% higher dissemination ratio on average.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A new lightweight data security system for data security in the cloud computing

引用

Measurement: Sensors 2023年 29卷

作者： Mohammed, Shameer Nanthini, S. Bala Krishna, N. Srinivas, Inumarthi V. Rajagopal, Manikandan Ashok Kumar, M. University of Technology and Applied Sciences Sur Oman Department of AI & DS Saveetha School of Engineering Saveetha Institute of Medical and Technical Science Thandalam Chennai India Department of CSE Mohan Babu University &SreeVidyanikethan Engineering College Andhrapradesh Tirupati517102 India Mumbai400077 India School of Business and Management Christ University Bangalore560029 India Faculty of Computer Science Department of Computer Science and Software Engineering Skyline University Nigeria Kano Nigeria

In recent decades, data has proved indispensable to all facets of human existence. The development of several applications has resulted in the exponential expansion of data. This information can be encrypted and stored in secure areas. Cloud computing is the technology that can be used to store these massive data sets. The article suggests a Cloud-based Data Security System (C-DSS) that employs a five-tiered trust model for cloud-edge data-sharing architectures. The data owner can select an appropriate trust level and Cyber Threat Information (CTI) sanitization procedure before releasing CTI for analytic strategy. In addition, this cleansing method is conducted either by an end device or by the cloud service supplier, based on the organization's degree of confidence in latter. Research presents the trust architecture, cloud architecture, and installation methodology, all of which are intended to meet widest variety of needs for exchanging secret CTI information. The testing findings high degree of data security and an evident improvement in terms of cypher processing time and security services when compared to the encryption systems that are most often employed in cloud technology. In conclusion, research briefly outlines development and evaluation performed so far by pilot applications confirming the architecture. © 2023 The Authors

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A Light Transfer Model for Chinese Named Entity Recognition for Specialty Domain 15th

A Light Transfer Model for Chinese Named Entity Recognition ...

引用

15th CCF Conference on computer Supported Cooperative Work and Social Computing, Chinese CSCW 2020

作者： Wu, Jiaqi Liu, Tianyuan Sun, Yuqing Gong, Bin School of Software Shandong University Jinan China Engineering Research Center of Digital Media Technology Shandong University Jinan China School of Computer Science and Technology Shandong University Jinan China

ISBN: (纸本)9789811625398

Named entity recognition (NER) for specialty domain is a challenging task since the labels are specific and there are not sufficient labelled data for training. In this paper, we propose a simple but effective method, named Light Transfer NER model (LTN), to tackle this problem. Different with most traditional methods that fine tune the network or reconstruct its probing layer, we design an additional part over a general NER network for new labels in the specific task. By this way, on the one hand, we can reuse the knowledge learned in the general NER task as much as possible, from the granular elements for combining inputs, to higher level embedding of outputs. On the other hand, the model can be easily adapted to the domain specific NER task without reconstruction. We also adopt the linear combination on each dimension of input feature vectors instead of using vector concatenation, which reduces about half parameters in the forward levels of network and makes the transfer light. We compare our model with other state-of-the-art NER models on real datasets against different quantity of labelled data. The experimental results show that our model is consistently superior than baseline methods on both effectiveness and efficiency, especially in case of low-resource data for specialty domain. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Light transmission

来源：评论

学校读者我要写书评

暂无评论

CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenario

arXiv

引用

arXiv 2023年

作者： Guo, Jingcai Guo, Song Ma, Shiheng Sun, Yuxia Xu, Yuanyuan The Department of Computing The Hong Kong Polytechnic University Hong Kong The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200030 China The Department of Computer Science Jinan University Guangzhou510632 China The School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China

We study the challenging task of malware recognition on both known and novel unknown malware families, called malware open-set recognition (MOSR). Previous works usually assume the malware families are known to the classifier in a close-set scenario, i.e., testing families are the subset or at most identical to training families. However, novel unknown malware families frequently emerge in real-world applications, and as such, require to recognize malware instances in an open-set scenario, i.e., some unknown families are also included in the test-set, which has been rarely and non-thoroughly investigated in the cyber-security domain. One practical solution for MOSR may consider jointly classifying known and detecting unknown malware families by a single classifier (e.g., neural network) from the variance of the predicted probability distribution on known families. However, conventional well-trained classifiers usually tend to obtain overly high recognition probabilities in the outputs, especially when the instance feature distributions are similar to each other, e.g., unknown v.s. known malware families, and thus dramatically degrades the recognition on novel unknown malware families. To address the problem and construct an applicable MOSR system, we propose a novel model that can conservatively synthesize malware instances to mimic unknown malware families and support a more robust training of the classifier. More specifically, we build upon the generative adversarial networks (GANs) to explore and obtain marginal malware instances that are close to known families while falling into mimical unknown ones to guide the classifier to lower and flatten the recognition probabilities of unknown families and relatively raise that of known ones to rectify the performance of classification and detection. A cooperative training scheme involving the classification, synthesizing and rectification are further constructed to facilitate the training and jointly improve the model p

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Dynamic personalized federated learning with adaptive differential privacy 23

Dynamic personalized federated learning with adaptive differ...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Xiyuan Yang Wenke Huang Mang Ye National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Hubei Luojia Laboratory Wuhan University Wuhan China

Personalized federated learning with differential privacy has been considered a feasible solution to address non-IID distribution of data and privacy leakage risks. However, current personalized federated learning methods suffer from inflexible personalization and convergence difficulties due to two main factors: 1) Firstly, we observe that the prevailing personalization methods mainly achieve this by personalizing a fixed portion of the model, which lacks flexibility. 2) Moreover, we further demonstrate that the default gradient calculation is sensitive to the widely-used clipping operations in differential privacy, resulting in difficulties in convergence. Considering that Fisher information values can serve as an effective measure for estimating the information content of parameters by reflecting the model sensitivity to parameters, we aim to leverage this property to address the aforementioned challenges. In this paper, we propose a novel federated learning method with Dynamic Fisher Personalization and Adaptive Constraint (FedDPA) to handle these challenges. Firstly, by using layer-wise Fisher information to measure the information content of local parameters, we retain local parameters with high Fisher values during the personalization process, which are considered informative, simultaneously prevent these parameters from noise perturbation. Secondly, we introduce an adaptive approach by applying differential constraint strategies to personalized parameters and shared parameters identified in the previous for better convergence. Our method boosts performance through flexible personalization while mitigating the slow convergence caused by clipping operations. Experimental results on CIFAR-10, FEMNIST and SVHN dataset demonstrate the effectiveness of our approach in achieving better performance and robustness against clipping, under personalized federated learning with differential privacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Semantic Trajectory Mining System Based on Deep Neural Network

A Semantic Trajectory Mining System Based on Deep Neural Net...

引用

第33届中国控制与决策会议

作者： Xinyuan Zhang Jiying Peng Xinqi Zhang School of Computer Science and Software Engineering University of Science and Technology Liaoning

At the beginning of 2020,epidemic of COrona VIrus Disease 19(COVID-19) broke *** the epidemic prevention and control,artificial intelligence,big data and other technologies have become powerful weapons against the epidemic,and have been widely used in the fields of epidemic tracing,confirming virus transmission path,resource allocation and so *** this study,BiLSTM-CRF model,Bootstrap and Tornado frameworks are used to implement a neural network-based semantic trajectory mining system for the COVID-19 *** the basis of collecting the data published by the health committees of various provinces and cities,the semantic trajectories of the patients are extracted to ensure the accuracy of the data and then establish mapping relationship between the real space and the text description of the trajectories of the patients,while taking the time and space factors into account and excavating the dynamic changes of the patients.

关键词： Bidirectional neural network Named entity recognition BiLSTM-CRF API

来源：评论

学校读者我要写书评

暂无评论

MSM-VC: High-fidelity Source Style Transfer for Non-Parallel Voice Conversion by Multi-scale Style Modeling

arXiv

引用

arXiv 2023年

作者： Wang, Zhichao Wang, Xinsheng Xie, Qicong Li, Tao Xie, Lei Tian, Qiao Wang, Yuping The ASLP Lab School of Computer Science Northwestern Polytechnical University Xi’an710072 China The School of Software Engineering Xi’an Jiaotong University Xi’an710049 China The ByteDance SAMI Group Shanghai200233 China

In addition to conveying the linguistic content from source speech to converted speech, maintaining the speaking style of source speech also plays an important role in the voice conversion (VC) task, which is essential in many scenarios with highly expressive source speech, such as dubbing and data augmentation. Previous work generally took explicit prosodic features or fixed-length style embedding extracted from source speech to model the speaking style of source speech, which is insufficient to achieve comprehensive style modeling and target speaker timbre preservation. Inspired by the style’s multi-scale nature of human speech, a multi-scale style modeling method for the VC task, referred to as MSM-VC, is proposed in this paper. MSM-VC models the speaking style of source speech from different levels, i.e., global, local, and frame levels. To effectively convey the speaking style and meanwhile prevent timbre leakage from source speech to converted speech, each level’s style is modeled by specific representation. Specifically, prosodic features, pre-trained ASR model’s bottleneck features, and features extracted by a model trained with a self-supervised strategy are adopted to model the frame, local, and global-level styles, respectively. Besides, to balance the performance of source style modeling and target speaker timbre preservation, an explicit constraint module consisting of a pre-trained speech emotion recognition model and a speaker classifier is introduced to MSM-VC. This explicit constraint module also makes it possible to simulate the style transfer inference process during the training to improve the disentanglement ability and alleviate the mismatch between training and inference. Experiments performed on the highly expressive speech corpus demonstrate that MSM-VC is superior to the state-of-the-art VC methods for modeling source speech style while maintaining good speech quality and speaker similarity. Furthermore, ablation analysis indicates the indi

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Robust Heterogeneous Federated Learning under Data Corruption

Robust Heterogeneous Federated Learning under Data Corruptio...

引用

International Conference on computer Vision (ICCV)

作者： Xiuwen Fang Mang Ye Xiyuan Yang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Hubei Luojia Laboratory Wuhan University Wuhan China

Model heterogeneous federated learning is a realistic and challenging problem. However, due to the limitations of data collection, storage, and transmission conditions, as well as the existence of free-rider participants, the clients may suffer from data corruption. This paper starts the first attempt to investigate the problem of data corruption in the model heterogeneous federated learning framework. We design a novel method named Augmented Heterogeneous Federated Learning (AugHFL), which consists of two stages: 1) In the local update stage, a corruption-robust data augmentation strategy is adopted to minimize the adverse effects of local corruption while enabling the models to learn rich local knowledge. 2) In the collaborative update stage, we design a robust re-weighted communication approach, which implements communication between heterogeneous models while mitigating corrupted knowledge transfer from others. Extensive experiments demonstrate the effectiveness of our method in coping with various corruption patterns in the model heterogeneous federated learning setting.

关键词：

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：