检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Jun Zhou, Jiantao Tian, Jinyu Sun, Weiwei Stake Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau China Faculty of Innovation Engineering Macau University of Science and Technology China Alibaba Group Hangzhou China

With the increasing prevalence of cloud computing platforms, ensuring data privacy during the cloud-based image related services such as classification has become crucial. In this study, we propose a novel privacy-preserving image classification scheme that enables the direct application of classifiers trained in the plaintext domain to classify encrypted images, without the need of retraining a dedicated classifier. Moreover, encrypted images can be decrypted back into their original form with high fidelity (recoverable) using a secret key. Specifically, our proposed scheme involves utilizing a feature extractor and an encoder to mask the plaintext image through a newly designed Noise-like Adversarial Example (NAE). Such an NAE not only introduces a noise-like visual appearance to the encrypted image but also compels the target classifier to predict the ciphertext as the same label as the original plaintext image. At the decoding phase, we adopt a Symmetric Residual Learning (SRL) framework for restoring the plaintext image with minimal degradation. Extensive experiments demonstrate that 1) the classification accuracy of the classifier trained in the plaintext domain remains the same in both the ciphertext and plaintext domains;2) the encrypted images can be recovered into their original form with an average PSNR of up to 51+ dB for the SVHN dataset and 48+ dB for the VGGFace2 dataset;3) our system exhibits satisfactory generalization capability on the encryption, decryption and classification tasks across datasets that are different from the training one;and 4) a high-level of security is achieved against three potential threat models. The code is available at https://***/csjunjun/***. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation

arXiv

引用

arXiv 2023年

作者： Hao, Zhiwei Guo, Jianyuan Han, Kai Tang, Yehui Hu, Han Wang, Yunhe Xu, Chang School of information and Electronics Beijing Institute of Technology China Huawei Noah’s Ark Lab Canada School of Computer Science Faculty of Engineering The University of Sydney Australia

Knowledge distillation (KD) has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme. However, most existing distillation methods are designed under the assumption that the teacher and student models belong to the same model family, particularly the hint-based approaches. By using centered kernel alignment (CKA) to compare the learned features between heterogeneous teacher and student models, we observe significant feature divergence. This divergence illustrates the ineffectiveness of previous hint-based methods in cross-architecture distillation. To tackle the challenge in distilling heterogeneous models, we propose a simple yet effective one-for-all KD framework called OFA-KD, which significantly improves the distillation performance between heterogeneous architectures. Specifically, we project intermediate features into an aligned latent space such as the logits space, where architecture-specific information is discarded. Additionally, we introduce an adaptive target enhancement scheme to prevent the student from being disturbed by irrelevant information. Extensive experiments with various architectures, including CNN, Transformer, and MLP, demonstrate the superiority of our OFA-KD framework in enabling distillation between heterogeneous architectures. Specifically, when equipped with our OFA-KD, the student models achieve notable performance improvements, with a maximum gain of 8.0% on the CIFAR-100 dataset and 0.7% on the ImageNet-1K dataset. PyTorch code1 and checkpoints can be found at https://***/Hao840/OFAKD. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Accurate and Efficient Privacy-Preserving Feature Extraction on Encrypted Images

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Zheng, Peijia Fang, Xiongjie Zhou, Zhipeng Yang, Rui Lu, Wei Cao, Xiaochun Huang, Jiwu Sun Yat-Sen University School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology MoE Key Laboratory of Information Technology Guangzhou510006 China Alibaba Group Hanzhou311121 China Shenzhen Campus of Sun Yat-sen University School of Cyber Science and Technology Shenzhen518100 China Shenzhen MSU-BIT University Guangdong Laboratory of Machine Perception and Intelligent Computing Faculty of Engineering Shenzhen518116 China

In cloud computing, it is necessary to outsource image processing algorithms securely without exposing private image content. The scale-invariant feature transform (SIFT) is a famous local descriptor widely used in computer vision. There are already some privacy-preserving schemes for computing SIFT on encrypted images. However, the state-of-the-art works have to convert fixed-point numbers into their binary representations, which reduces efficiency and accuracy. In this paper, we propose a novel privacy-preserving SIFT scheme built from secure protocols designed explicitly for fixed-point numbers to solve this problem. Specifically, using RLWE-based homomorphic encryption, we propose word-wise protocols to perform secure division, square root operation, comparison, derivation, and matrix inversion in a single-instruction multiple-data manner. These protocols allow direct processing of fixed-point numbers without converting them to binary numbers, thus achieving high computational efficiency. We have also realized critical SIFT steps missing from previous works, including Euclidean gradient amplitude computation, histogram peak interpolation, and precise interval localization, leading to improved accuracy of SIFT features in the encrypted domain. We conduct security analysis and perform extensive experiments to evaluate the execution efficiency and accuracy. The experimental results show that the proposed scheme outperforms the state-of-the-art works in terms of computational efficiency and accuracy. © 2004-2012 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Text Classification for Judicial Texts via Dual Graph and Label Feature Fusion

Multi-Label Text Classification for Judicial Texts via Dual ...

引用

Smart World Congress (SWC), IEEE

作者： Qiliang Gu Qin Lu Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

The legal judgement prediction (LJP) of judicial texts represents a multi-label text classification (MLTC) problem, which in turn involves three distinct tasks: the prediction of charges, legal articles, and terms of penalty. Nevertheless, extant multi-label text classification models tend to eschew the consideration of multiple correlations and semantic information between labels when predicting judicial texts, which may result in the loss of pertinent information. Furthermore, these models do not take full advantage of the local and overall information of the labels in the process of selecting appropriate labels for the text using the multi-head attention mechanism. To address these issues, we propose a new model, BGFLFF, which explores label correlation and semantics among the three tasks by employing Graph Convolutional Network (GCN) and multi-head attention mechanisms. In particular, we propose a Bi-Graph Fusion GCN (BGF-GCN), which fuses the co-occurrence matrix of labels with the cosine similarity matrix, thereby fully exploiting the multiple correlations between labels. Furthermore, prior to embedding the tags, the interpretations of the labels are obtained via Google in order to enhance the semantic information between the labels. To further reinforce the interconnections between labels and text and more effectively comprehend the interrelationships between the three tasks, we propose a Multi-Head Label Feature Fusion Attentional Mechanism (MH-LFFAtt), which assigns distinct weights to the pertinent label information in the text by fusing the local and overall features of the labels. The experimental results demonstrate that the F1 score exhibits an improvement of up to ${2. 2 8 \%}$ and a minimum of ${1. 2 9 \%}$ across the various tasks of the two datasets. This evidence substantiates the assertion that BGFLFF outperforms the existing baseline model.

关键词： Attention mechanisms Correlation Law Graph convolutional networks Fuses Text categorization Semantics Predictive models Multitasking Internet

来源：评论

学校读者我要写书评

暂无评论

Protein Complex Identification Method based on Weighted Subgraph Clustering and Biocompatibility Evaluation

Protein Complex Identification Method based on Weighted Subg...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tie Hua Zhou Wanlin Zhang Ling Wang Xiaoyan Xia Keun Ho Ryu School of Computer Science Northeast Electric Power University Jilin China Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Vietnam College of Electrical and Computer Engineering Chungbuk National University Cheongju Republic of Korea

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

In this paper, we proposed a Weighted Subgraph Clustering for Protein Complex Identification (WSC-PCI) method , which combined with Gene Ontology (GO) annotations and improved Edge Clustering Coefficient (ECC) to indentify the protein complex over weighted Protein- Protein Interaction (PPI) network. By using the comprehensive weighted method to calculate the node weights within the PPI network, in order to mine the valuable and core subgraphs, which are related to the biologically significant and real protein complexes based on the core-attachment structure requirements. And then, calculating Biocompatibility value (BA-value) to identify potential proteins, which have more stable and good biocompatibility. By comparing with multiple algorithms on real datasets of different species, the results show that WSC-PCI outperforms other methods with regard to recall, precision and MMR, and the authenticity and biological significance of the identification results are verified by p-value analysis.

关键词： Proteins Protein engineering Accuracy Annotations Clustering methods Clustering algorithms Ontologies Biology Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Web Service Ranking based on QoS and Use Preference

Web Service Ranking based on QoS and Use Preference

引用

Conference on information and Knowledge technology

作者： Seyed Hossein Siadat Danial Ramezani Fatemeh Ahani Department of Operation Management and Information Technology Faculty of Management Kharazmi University Tehran Iran Faculty of Electrical Engineering Computer and Information Technology Islamic Azad University Qazvin Iran Department of Computer Science Islamic Azad University Iran

ISBN: (纸本)9798350320633

One of the most important issues of ranking is thousands of web service available. Finding and implementing algorithms that do ranking well, is very essential. The important issue is that after ranking and choosing their best by different algorithms and suggesting them to user he is satisfied. Different algorithms presented so far for this purpose have focused on processing the content of user application and they have tried to do this selection based on word key or meaning or quality features, yet psychological features of users has impact on their satisfaction of suggested services of algorithms which hasn't been noted to this dependency. The purpose of this research is ranking web services and suggesting their best considering psychological features of persons. We review 2 ways of ranking. At first using qualitative model we consider qualitative features and then psychological features in qualitative and psychological combined model besides qualitative features. In qualitative and psychological combined model psychological valid test NEO-FFI has been used to get people psychological features and put them in related clusters given persons psychological features, on one hand, we obtain the amount of people importance to qualitative features using “prioritizing to web services features” form and then the relationships between persons psychological features and qualitative features of services are computed and Correlation coefficients indicating the importance of the qualitative feature in terms of each cluster persons are obtained and we can obtain the amount of general quality of each web service by its impact on qualitative features of data base of real life of QWS consisting 2500 web services and rank them and suggest the best to user. Above forms (given kokran formula) were distributed among 66 IT experts from 5 universities. At last 10 services which were suggested by qualitative and qualitative and psychological combined models, gave to 20 users for 14 days an

关键词： Knowledge engineering Correlation coefficient Web services Psychology Quality of service Data models

来源：评论

学校读者我要写书评

暂无评论

NCOD: Near-Optimum Video Compression for Object Detection

NCOD: Near-Optimum Video Compression for Object Detection

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Ardavan Elahi Ali Falahati Farhad Pakdaman Mehdi Modarressi Moncef Gabbouj School of Electrical and Computer Engineering College of Eng. University of Tehran Iran Avanco.tech Faculty of Information Technology and Communication Sciences Tampere University Finland

With the emergence of technologies like smart cities, Internet of things (IoT), and 5G, the amount of produced visual data at the edges and remote nodes has exploded. Since for a considerable portion of the captured video the target is a machine learning task, rather than a human audience, transmission of videos in such applications requires efficient video compression tailored for machine vision. However, existing compression solutions are optimized for human vision. This paper presents a methodology to optimize an existing video compression standard, HEVC, for a machine vision task, Object Detection (OD). To this end, (1) a dataset of compressed videos, including several compression-ratios and their corresponding OD performance is collected to enable modeling, (2) A trade-off point (knee-point) between bitrate and OD performance is defined, that finds the point after which no major improvements will be achieved, (3) a set of features were extracted and studied to model this point, via a practical machine learning method. The resulting solution can predict the knee-point with $\boldsymbol{\text{MAE}=1.28}$ , resulting in a ∆Recall of only 0.012 and bitrate reduction of 86.56%, compared to OD with very high-quality video.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained Devices

arXiv

引用

arXiv 2024年

作者： Xu, Yongqi Lee, Yujian Yi, Gao Liu, Bosheng Chen, Yucong Liu, Peng Wu, Jigang Chen, Xiaoming Han, Yinhe Computer Science and Technology Guangdong University of Technology China Faculty of Science and Technology Beijing Normal University Hong Kong Baptist University United International College China School of Information Science and Engineering Lanzhou University China Institute of Computing Technology Chinese Academy of Sciences China

Deep neural networks (DNNs) are powerful for cognitive tasks such as image classification, object detection, and scene segmentation. One drawback however is the significant high computational complexity and memory consumption, which makes them unfeasible to run real-time on embedded platforms because of the limited hardware resources. Block floating point (BFP) quantization is one of the representative compression approaches for reducing the memory and computational burden owing to their capability to effectively capture the broad data distribution of DNN models. Unfortunately, prior works on BFP-based quantization empirically choose the block size and the precision that preserve accuracy. In this paper, we develop a BFP-based bitwidth-aware analytical modeling framework (called "BitQ") for the best BFP implementation of DNN inference on embedded platforms. We formulate and resolve an optimization problem to identify the optimal BFP block size and bitwidth distribution by the trade-off of both accuracy and performance loss. Experimental results show that compared with an equal bitwidth setting, the BFP DNNs with optimized bitwidth allocation provide efficient computation, preserving accuracy on famous benchmarks. The source code and data are available at https://***/Cheliosoops/BitQ. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Assessing Students for Industry Readiness using Classification Methods 9

Assessing Students for Industry Readiness using Classificati...

引用

9th ACIS International Virtual Conference on Applied Computing and information technology, ACIT 2022

作者： Hossain Molla, Jakir Basak, Sandip Kumar Obaidullah, Sk Md Alam, Parveen Ahmed Goto, Takaaki Sen, Soumya Department of Computer Science and Engineering Aliah University India Department of Data Science Friedrich-Alexander-Universität Germany Department of Management & Business Administration Aliah University India Faculty of Information Sciences and Arts Toyo University Japan A.K.Choudhury School of Information Technology University of Calcutta India

ISBN: (纸本)9781450397605

Although Placement of students is an intrinsic requirement for the students worldwide majorly for professional as well as for higher degree courses. However, often the students are not aware about their skill levels that are considered as the industry readiness parameters. The Institutions often take care of the students to upgrade the skill level to meet the requirement of the Industry. In order to analyze the students based on the several parameters of industry readiness intelligent methods are required to assess them. In this research work, different classification methods are applied on the existing placement data to evaluate whether a student will get a job or not. Accuracies of these methods are compared using a real life data set. This analysis will help the Institutes to take the decision how long the training programs will continue. The result of the classification methods have been improved further using Random oversampling. © 2022 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Two-Operation Buffering based on Dynamic Optical RAM

Two-Operation Buffering based on Dynamic Optical RAM

引用

International Conference on Modern Problems of Radio engineering, Telecommunications and computer Science

作者： Andriy Semenov Serhii Tsyrulnyk Serhii Baraban Olena Semenova Andrii Rudyk Anton Khloba Faculty of Information Electronic Systems Vinnytsia National Technical University Vinnytsia Ukraine Department of Computer Sciences and Digital Economy Vinnytsia National Agrarian University Vinnytsia Ukraine Faculty of Computing and Telecommunications Poznan University of Technology Poznan Poland Department of Automation Electrical Engineering and Computer-Integrated Technologies National University of Water and Environmental Engineering Rivne Ukraine

ISBN: (数字)9798331520564

ISBN: (纸本)9798331520571

The authors of this paper propose a block diagram for a dual-operating buffer on a dynamic optical RAM. The buffer consists of two dynamic optical RAMs, each controlled separately to allow for simultaneous writing and reading of data, thereby improving performance. This setup enables data to be read from the buffer while new data is being written to it. Implementing a dual-operating buffer on a dynamic optical RAM has the potential to enhance the performance of high-speed data transmission in telecommunications networks. The authors conducted numerical calculations to compare failure probabilities between single-operation and dual-operation buffers on dynamic optical RAM. The results indicated that using a dual-operating buffer significantly reduces the probability of failure with the same buffer memory capacity compared to a single-operating buffer. Additionally, the authors analyzed the effectiveness of the proposed dual-operating buffer. The analysis confirmed that exploiting dynamic optical memory for buffering enhances data transfer speed and efficiency due to the inherent properties of optical data transfer, such as high bandwidth and low latency.

关键词： Optical buffering Random access memory Probability Optical fiber networks Writing Data transfer Software Telecommunications High-speed optical techniques Capacity planning

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：