检索结果-内蒙古大学图书馆

6th International Conference on Frontier Technologies of Information and Computer, ICFTIC 2024

作者： Wei, Chunyuan Yuan, Chuan Qi, Yu Xu, Bangjian Niu, Xin College of Computer Science and Electronic Engineering Hunan University Changsha China College of Electrical and Information Engineering Hunan University Changsha China College of Computer National University of Defense Technology Science and Technology on Parallel and Distributed Laboratory Changsha China

ISBN: (纸本)9798331541750

With the rapid advancement of artificial intelligence, chips have become increasingly important. The emerging RISC-V instruction set gradually provides powerful computing support for this field. In this context, along with the computing requirements of deep learning, this paper presents the design of a high-performance floating-point arithmetic logic unit (FALU) that facilitates calculations with double-precision, single-precision, half-precision, and Bfloat16 precision data. This design is based on a single-channel algorithm with merged rounding. It improves and implements a composite adder that combines high and low bits. It also proposes a tree-like floating-point comparator based on the Kogge-Stone parallel prefix network. To ensure that the FALU components meet performance requirements, we undergo functional verification in the Vivado simulation environment. Operating at 1.47GHz under the 28nm CMOS process, the components achieve the predetermined performance indicators. © 2024 IEEE.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning:a survey

引用

Frontiers of Information technology & Electronic Engineering 2020年第12期21卷 1726-1744页

作者： Hao-nan WANG Ning LIU Yi-yun ZHANG Da-wei FENG Feng HUANG Dong-sheng LI Yi-ming ZHANG Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangsha 41OOOOChina

Deep reinforcement learning(RL)has become one of the most popular topics in artificial intelligence *** has been widely used in various fields,such as end-to-end control,robotic control,recommendation systems,and natural language dialogue *** this survey,we systematically categorize the deep RL algorithms and applications,and provide a detailed review over existing deep RL algorithms by dividing them into modelbased methods,model-free methods,and advanced RL *** thoroughly analyze the advances including exploration,inverse RL,and transfer ***,we outline the current representative applications,and analyze four open problems for future research.

关键词： Reinforcement learning Deep reinforcement learning Reinforcement learning applications

来源：评论

学校读者我要写书评

暂无评论

A prompt-based approach to adversarial example generation and robustness enhancement

引用

Frontiers of Computer science 2024年第4期18卷 85-96页

作者： Yuting YANG Pei HUANG Juan CAO Jintao LI Yun LIN Feifei MA Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China Department of Computer Science Stanford UniversityCA 94305USA School of Computing National University of SingaporeSingapore 119077Singapore Laboratory of Parallel Software and Computational Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China

Recent years have seen the wide application of natural language processing(NLP)models in crucial areas such as finance,medical treatment,and news media,raising concerns about the model robustness and *** find that prompt paradigm can probe special robust defects of pre-trained language *** prompt texts are first constructed for inputs and a pre-trained language model can generate adversarial examples for victim models via *** results show that prompt paradigm can efficiently generate more diverse adversarial examples besides synonym ***,we propose a novel robust training approach based on prompt paradigm which incorporates prompt texts as the alternatives to adversarial examples and enhances robustness under a lightweight minimax-style optimization *** on three real-world tasks and two deep neural models show that our approach can significantly improve the robustness of models to resist adversarial attacks.

关键词： robustness adversarial example prompt learning pre-trained language model

来源：评论

学校读者我要写书评

暂无评论

Word Embedding-based Context-sensitive Network Flow Payload Anomaly Detection 3

Word Embedding-based Context-sensitive Network Flow Payload ...

引用

3rd International Conference on Applied Machine Learning, ICAML 2021

作者： Li, Yizhou Wang, Yijie Cheng, Li Xu, Hongzuo Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha China

ISBN: (纸本)9781665421256

Payload anomaly detection can discover malicious beliaviors tiidden in network packets. It is liard to liandle payload due to its various possible characters and complex semantic context, and tlius identifying abnormal payload is also a non-trivial task. Prior art only uses the n-gram language model to extract features, which directly leads to ultra-high-dimensional feature space and also fails to capture the context semantics fully. Accordingly, this paper proposes a word embedding-based context-sensitive network flow payload anomaly detection method (termed WECAD). First, WECAD obtains the initial feature representation of the payload through the word embedding-based method. Then, we propose a corpus pruning algorithm, which appUes the cosine similarity clustering and frequency distribution to prune inconsequential characters. We only keep the essential characters to reduce the calculation space. Subsequently, we propose a context learning algorithm. It employs the co-occurrence matrix transformation technology and introduces the backward step size to consider the order relationship of essential characters. Comprehensive experiments on real-world intrusion detection datasets validate the effectiveness of our method. © 2021 IEEE

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Neural Network Model for Credit Risk Prediction of Chinese Farmers 6

A Novel Deep Neural Network Model for Credit Risk Prediction...

引用

6th IEEE International Conference on Data science in Cyberspace, DSC 2021

作者： Xie, Yalong Li, Aiping Liu, Ziniu Chen, Kai Tu, Hongkui College Of Computer National University Of Defense Technology Science And Technology On Parallel And Distributed Processing Laboratory Changsha China

ISBN: (纸本)9781665418157

China is a big agricultural county with more than 500 million rural population. In China, farmers usually loan from rural commercial banks or rural credit cooperatives. It is crucial for the national economic development and the improvement of people's standard of living that how to reasonably use funds to subsidize the agricultural population and reduce the risk of rural loans. At present, credit risk prediction of farmers mainly depends on the experience of experts in the business field, and there is little published research on using artificial intelligence methods to solve this problem. This paper presents a complete set of methods, including data collection, feature selection, etc. We propose a novel deep neural network model named DNN-CRP for credit risk prediction of Chinese framers. Experiments on an actual credit loan dataset of Chinese farmers are presented, and experimental results show that the comprehensive performance of the DNN-CRP model is better than current state-of-the-art models. It is believed that the DNN-CRP model proposed in this paper can help banks improve the efficiency of the credit loan business of farmers and reduce credit risks. © 2021 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Multi-Layer Feature Division Transferable Adversarial Attack

Multi-Layer Feature Division Transferable Adversarial Attack

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Zikang Jin Changchun Yin Piji Li Lu Zhou Liming Fang Xiangmao Chang Zhe Liu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China Science and Technology on Parallel and Distributed Processing Laboratory (PDL) China

Improving the transferability of adversarial examples for the purpose of attacking unknown black-box models has been intensively studied. In particular, feature-level transfer-based attacks, which destroy the intermediate feature outputs of source models, are proven to generate more transferable adversarial examples. However, existing state-of-the-art feature-level attacks only destroy a single intermediate layer, this severely limits the transferability of adversarial examples. And all of these attacks have a vague distinction between positive and negative features. By contrast, we propose the Multi-layer Feature Division Attack (MFDA), which aggregates multi-layer feature information on the basis of feature division to attack. Extensive experimental evaluation demonstrates that MFDA can significantly boost the adversarial transferability and quantitatively distinguish the effects of positive and negative features on transferability. Compared to the state-of-the-art feature-level attacks, our improvement methods with MFDA increase the average success rate by 2.8% against normally trained models and 3.0% against adversarially trained models.

关键词： Aggregates Closed box Signal processing Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

EdgeAnchor: A Rapid and Balanced File Storage Strategy at the Network Edge

EdgeAnchor: A Rapid and Balanced File Storage Strategy at th...

引用

International Conference on parallel and distributed Systems (ICPADS)

作者： Han Liu Xingrui Xie Zhuopu Zhang Geyao Cheng Lailong Luo Deke Guo Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology National Laboratory for Parallel and Distributed Processing National University of Defense Technology

Storing files at the network edge has become a new paradigm of storage systems, which is promising to mitigate network congestion and reduce file retrieval latency. However, the traditional file storage scheme cannot effectively meet the requirements of rapid indexing and load balance when applied directly to the edge. Moreover, due to the dynamic nature of the edge environment where edge servers can join or leave at will, it is necessary for the storage scheme to adjust with minimal disruption. In this paper, we propose EdgeAnchor, a novel edge storage strategy that is composed of the two-layer hash mappings. The first layer, file-to-bucket mapping, adopts the pseudo-deletion algorithm to deal with the variations in file size, while the second layer utilizes the multiple bucket-to-server mapping to adapt to the heterogeneity in the servers’ storage capacities. Furthermore, EdgeAnchor constructs a list of deleted or added working sets for each bucket and creates a dictionary for the mappings between buckets and edge servers. In the manner, EdgeAnchor ensures a rapid file index and balances server load at the dynamic network edge. We also attach the mathematical analyses to EdgeAnchor, which theoretically proves its logarithmic complexity of hash operations and memory accesses. The experiments conducted on real-world datasets demonstrate that EdgeAnchor achieves the file index throughput twice as high as that of Consistent Hashing, under the constraints of load balance. Additionally, it ensures a low and stable data migration volume, when adding or removing edge servers consecutively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Differentially Private and Heterogeneity-Robust Federated Learning With Theoretical Guarantee

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6369-6384页

作者： Wang, Xiuhua Wang, Shuai Li, Yiwei Fan, Fengrui Li, Shikang Lin, Xiaodong Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China Xiamen University of Technology Fujian Key Laboratory of Communication Network and Information Processing Xiamen361024 China University of Guelph School of Computer Science GuelphONN1G 2W1 Canada

Federated learning (FL) is a popular distributed paradigm where enormous clients collaboratively train a machine learning (ML) model under the orchestration of a central server without knowing the clients' private raw data. The development of effective FL algorithms faces multiple practical challenges including data heterogeneity and clients' privacy protection. Despite that numerous attempts have been made to deal with data heterogeneity or rigorous privacy protection, none have effectively tackled both issues simultaneously. In this article, we propose a differentially private and heterogeneity-robust FL algorithm, named DP-FedCVR to mitigate the data heterogeneity by following the client-variance-reduction strategy. Besides, it adopts a sophisticated differential privacy (DP) mechanism where the privacy-amplified strategy is applied, to achieve a rigorous privacy protection guarantee. We show that the proposed DP-FedCVR algorithm maintains its heterogeneity-robustness though DP noises are incorporated, while achieving a sublinear convergence rate for a nonconvex FL problem. Numerical experiments based on image classification tasks are presented to demonstrate that DP-FedCVR provides superior performance over the benchmark algorithms in the presence of data heterogeneity and various DP privacy budgets. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Model Provenance Management in MLOps Pipeline 2022

Model Provenance Management in MLOps Pipeline

引用

8th International Conference on Computing and Data Engineering, ICCDE 2022

作者： Mei, Songzhu Liu, Cong Wang, Qinglin Su, Huayou Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology China Information Center Cmc Logistic Support Department China

ISBN: (纸本)9781450395717

Machine learning engineering is an important technology that has attracted the attention of academia and industry in the past two years. For AI to become a productivity of enterprises, it must be engineered to solve the problems of model development, deployment, management, prediction, and other lifecycle management, and MLOps system is the most concerned technology in the current machine learning engineering process. This paper starts from the training evolution process of intelligent computing models in machine learning engineering, focuses on the influence of data, training algorithms, and requirement indicators on the model evolution process, and gives the definition of Model Provenance and its evolutionary correlation elements. Based on the concept of model lineage, this paper designs a method to manage the model evolution process in the MLOps system and implements the related system. © 2022 Association for Computing Machinery. All rights reserved.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

DaBA: Data-free Backdoor Attack against Federated Learning via Malicious Server

DaBA: Data-free Backdoor Attack against Federated Learning v...

引用

Image processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Kuiqi Chen Liming Fang Mengxin Wang Changchun Yin College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Science and Technology on Parallel and Distributed Processing Laboratory (PDL) Changsha China

Current research shows that the privacy of FL is threatened by an honest-but-curious server. However, existing research focus on privacy attacks against the malicious server while overlooking that it could also compromise the shared model's integrity by introducing poisoning attacks. In this work, we propose a novel data-free backdoor attack (DaBA) against FL via malicious server to bridge the gap. Specifically, we utilize global model inversion to obtain a dummy dataset on the server side, then add backdoor triggers to a portion of the inputs in the dummy dataset and replace their labels with the target label, and finally retrain part of the global model on the poisoned dummy dataset. Our experimental results show that DaBA can achieve a high attack success rate on poisoned samples and high prediction accuracy on clean samples, which means the effectiveness and stealthiness of DaBA, respectively. For example, in the experiment of the MNIST dataset, DaBA can achieve a 99.6% attack success rate and 96.3% accuracy rate. We also discuss possible defense strategies against our attack. Our research reveals a significant security risk of FL.

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：