检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Tianyang Xu, Peng Picek, Stjepan Luo, Bo Susilo, Willy Jin, Hai Liang, Kaitai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering China Cluster and Grid Computing Lab School of Computer Science and Technology China Huazhong University of Science and Technology Wuhan430074 China Digital Security Group Radboud University Nijmegen Netherlands Department of EECS Institute of Information Sciences The University of Kansas LawrenceKS United States Institute of Cybersecurity and Cryptology School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft2628 CD Netherlands

Dynamic searchable symmetric encryption (DSSE) enables users to delegate the keyword search over dynamically updated encrypted databases to an honest-but-curious server without losing keyword privacy. This paper studies a new and practical security risk to DSSE, namely, secret key compromise (e.g., a user’s secret key is leaked or stolen), which threatens all the security guarantees offered by existing DSSE schemes. To address this open problem, we introduce the notion of searchable encryption with key-update (SEKU) that provides users with the option of non-interactive key updates. We further define the notion of post-compromise secure with respect to leakage functions to study whether DSSE schemes can still provide data security after the client’s secret key is compromised. We demonstrate that post-compromise security is achievable with a proposed protocol called "Bamboo". Interestingly, the leakage functions of Bamboo satisfy the requirements for both forward and backward security. We conduct a performance evaluation of Bamboo using a real-world dataset and compare its runtime efficiency with the existing forward-and-backward secure DSSE schemes. The result shows that Bamboo provides strong security with better or comparable performance. © 2024, CC BY.

关键词： Bamboo

来源：评论

学校读者我要写书评

暂无评论

Not all diffusion model activations have been evaluated as discriminative features 24

Not all diffusion model activations have been evaluated as d...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Benyuan Meng Qianqian Xu Zitai Wang Xiaochun Cao Qingming Huang Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at https://***/Darkbblue/generic-diffusion-feature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

D4M: dataset Distillation via Disentangled Diffusion Model

D4M: Dataset Distillation via Disentangled Diffusion Model

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Duo Su Junjie Hou Weizhi Gao Yingjie Tian Bowen Tang UCAS School of Computer Science and Technology Research Center on Fictitious Economy and Data Science CAS Key Laboratory of Big Data Mining and Knowledge Management CAS UCAS Sino-Danish College Department of Computer Science NCSU UCAS School of Economics and Management UCAS MOE Social Science Laboratory of Digital Economic Forecasts and Policy Simulation CAS Institute of Computing Technology

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

dataset distillation offers a lightweight synthetic dataset for fast network training with promising test accuracy. To imitate the performance of the original dataset, most approaches employ bi-level optimization and the distillation space relies on the matching architecture. Nevertheless, these approaches either suffer significant computational costs on large-scale datasets or experience performance decline on cross-architectures. We advocate for designing an economical dataset distillation framework that is independent of the matching architectures. With empirical observations, we argue that constraining the consistency of the real and synthetic image spaces will enhance the cross-architecture generalization. Motivated by this, we introduce dataset Distillation via Disentangled Diffusion Model (D 4 M), an efficient framework for dataset distillation. Compared to architecture-dependent methods, D 4 M employs latent diffusion model to guarantee consistency and incorporates label information into category prototypes. The distilled datasets are versatile, eliminating the need for repeated generation of distinct datasets for various architectures. Through comprehensive experiments, D4M demonstrates superior performance and robust generalization, surpassing the SOTA methods across most aspects.

关键词： Training Computer vision Computational modeling Prototypes Computer architecture Diffusion models Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

databench-T:A Transactional database Benchmark for Financial Scenarios

Databench-T:A Transactional Database Benchmark for Financial...

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Chunyu Jiang Jiafeng Tian Pengwei Ma Cloud Computing and Big Data Research Institute China Academy of Information and Communication Technology Beijing China

ISBN: (纸本)9781665416597

This paper reviewed current transactional database benchmark, especially TPC-C. There are some limitations to apply TPC-C into financial industry for benchmarking transactional database. In order to simulate real financial business, the project member has designed a benchmark named databench-T, which is based on money transfer scenario. The model and workloads of the benchmark is introduced in detail in this paper. The benchmark is implemented by project members to provide a unified toolkit. To run a test, there are four steps: toolkit installation, data generation, workload execute and results display. All those steps are presented in the paper.

关键词： Java data privacy databases Conferences Benchmark testing Security Usability

来源：评论

学校读者我要写书评

暂无评论

Vision-Amplified Semantic Entropy for Hallucination Detection in Medical Visual Question Answering

arXiv

引用

arXiv 2025年

作者： Liao, Zehui Hu, Shishuai Zou, Ke Fu, Huazhu Zhen, Liangli Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Institute of High Performance Computing Agency for Science Technology and Research Singapore138632 Singapore National University of Singapore Singapore119077 Singapore

Multimodal large language models (MLLMs) have demonstrated significant potential in medical Visual Question Answering (VQA). Yet, they remain prone to hallucinations—incorrect responses that contradict input images, posing substantial risks in clinical decision-making. Detecting these hallucinations is essential for establishing trust in MLLMs among clinicians and patients, thereby enabling their real-world adoption. Current hallucination detection methods, especially semantic entropy (SE), have demonstrated promising hallucination detection capacity for LLMs. However, adapting SE to medical MLLMs by incorporating visual perturbations presents a dilemma. Weak perturbations preserve image content and ensure clinical validity, but may be overlooked by medical MLLMs, which tend to over rely on language priors. In contrast, strong perturbations can distort essential diagnostic features, compromising clinical interpretation. To address this issue, we propose Vision Amplified Semantic Entropy (VASE), which incorporates weak image transformations and amplifies the impact of visual input, to improve hallucination detection in medical VQA. We first estimate the semantic predictive distribution under weak visual transformations to preserve clinical validity, and then amplify visual influence by contrasting this distribution with that derived from a distorted image. The entropy of the resulting distribution is estimated as VASE. Experiments on two medical open-ended VQA datasets demonstrate that VASE consistently outperforms existing hallucination detection methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SASA-Net: A spatial-aware self-attention mechanism for building protein 3D structure directly from inter-residue distances

SASA-Net: A spatial-aware self-attention mechanism for build...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Gong, Tiansu Ju, Fusong Sun, Shiwei Bu, Dongbo Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Zhongke Big Data Academy Henan Zhengzhou450046 China

ISBN: (纸本)9781665401265

Protein structure prediction has achieved considerable progresses mainly due to the increased accuracy of inter-residue distance estimation and the application of deep learning *** of the distance-based ab initio prediction approaches adopt a two-step diagram: constructing a potential function based on the estimated inter-residue distances, and then build a 3D structure that minimizes the potential function. These approaches have proven very promising;however, they still suffer from several limitations, especially the inaccuracies incurred by the handcrafted potential ***, we present SASA-Net, a deep learning-based approach that directly learns protein 3D structure from the estimated inter-residue distances. Unlike the existing approach simply representing protein structures as coordinates of atoms, SASA-Net represents protein structures using pose of residues, i.e., the coordinate system of each individual residue in which all backbone atoms of this residue are fixed. The key element of SASA-Net is a spatial-aware self-attention mechanism, which is able to adjust a residue's pose according to all other residues' features and the estimated distances between residues. By iteratively applying the spatial-aware self-attention mechanism, SASA-Net continuously improves the structure and finally acquires a structure with high accuracy. Using the CATH35 proteins as representatives, we demonstrate that SASA-Net is able to accurately and efficiently build structures from the estimated inter-residue distances. The high accuracy and efficiency of SASA-Net enables an end-to-end neural network model for protein structure prediction through combining SASA-Net and an neural network for inter-residue distance prediction. Source code of SASA-Net is available at https://*** gongtiansu/SASA-Net/ © 2021 IEEE.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

TA-MoE: topology-aware large scale mixture-of-expert training 22

TA-MoE: topology-aware large scale mixture-of-expert trainin...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Chang Chen Min Li Zhihua Wu Dianhai Yu Chao Yang Center for Data Science Peking University School of Mathematics Sciences Peking University and National Engineering Laboratory for Big Data Analysis and Applications Peking University Baidu Inc. School of Mathematics Sciences Peking University and National Engineering Laboratory for Big Data Analysis and Applications Peking University and Institute for Computing and Digital Economy Peking University

ISBN: (纸本)9781713871088

Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the model design or system optimization perspective, existing MoE dispatch patterns are still not able to fully exploit the underlying heterogeneous network environments. In this paper, we propose TA-MoE, a topology-aware routing strategy for large-scale MoE trainging, from a model-system co-design perspective, which can dynamically adjust the MoE dispatch pattern according to the network topology. Based on communication modeling, we abstract the dispatch problem into an optimization objective and obtain the approximate dispatch pattern under different topologies. On top of that, we design a topology-aware auxiliary loss, which can adaptively route the data to fit in the underlying topology without sacrificing the model accuracy. Experiments show that TA-MoE can substantially outperform its counterparts on various hardware and model configurations, with roughly 1.01x-1.61x, 1.01x-4.77x, 1.25x-1.54x improvements over the popular DeepSpeed-MoE, FastMoE and FasterMoE systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Type 2 Diabetes Mellitus Prediction Using data Mining Approach

Type 2 Diabetes Mellitus Prediction Using Data Mining Approa...

引用

computing (ICOCO), IEEE International Conference on

作者： Allina Farina Halias Nurain Hazeeqah Saiful Nurain Ibrahim Siti Afiqah Muhamad Jamil Mahayaudin M. Mansor Ahmad Zia Ul - Saufie Nor Azura Md Ghani School of Mathematical Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam Selangor Malaysia Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Kompleks Al-Khawarizmi Universiti Teknologi MARA Shah Alam Selangor Malaysia

Diabetes mellitus is a chronic, long-term condition that significantly impacts public health and socioeconomic growth worldwide. It has been established that risk prediction models can benefit clinical management decisions by targeting patients at a higher risk of developing type 2 diabetes. This metric is critical for those at a higher risk of developing type 2 diabetes mellitus regarding healthcare and lifestyle changes. As a result, this study aims to uncover significant risk factors for type 2 diabetes mellitus classification. Another goal of this research is to discover the best prediction models by assessing the accuracy rate of each model. This study employs several classification models, includinglogistics regression, decision tree and naïve bayes. Moreover, several feature selection methods are employed in the classification model: forward selection, backward elimination and optimized selection (evolutionary). The analysis was conducted by using Diabetes BRFSS2015 dataset, which is obtained from Kaggle website. This dataset consists of 76902 observations with 20 explanatory variables and one target variable with dichotomous classification. The study's findings show that only eight of the 20 risk factors in the prediction models are identified as significant. Age, GenHlth, Sex, HvyAlcoholConsump, HighBP, HighChol, NoDocbcNoCost, and Veggies are all important riskfactors. Furthermore, among the nine prediction models, logistic regression with optimal selection had the highest accuracy rate of 75.61%. As a result, logistic regression with the optimum selection approach is the best model for predicting the prevalence of type 2 diabetes type. The study hopes to promote awareness and provide more insight into the risk factors for type 2 diabetes. Type 2 diabetes could be correctly predicted and recognised early, resulting in prompt, effective treatments and reduced consequences.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RAGRAPH: A General Retrieval-Augmented Graph Learning Framework

arXiv

引用

arXiv 2024年

作者： Jiang, Xinke Qiu, Rihong Xu, Yongxin Zhang, Wentao Zhu, Yichen Zhang, Ruizhe Fang, Yuchen Chu, Xu Zhao, Junfeng Wang, Yasha School of Computer Science Peking University China University of Electronic Science and Technology of China China Center on Frontiers of Computing Studies Peking University Beijing China Big Data Technology Research Center Nanhu Laboratory Jiaxing China Peking University Information Technology Institute Binhai Tianjin China

Graph Neural Networks (GNNs) have become essential in interpreting relational data across various domains, yet, they often struggle to generalize to unseen graph data that differs markedly from training instances. In this paper, we introduce a novel framework called General Retrieval-Augmented Graph Learning (RAGRAPH), which brings external graph data into the general graph foundation model to improve model generalization on unseen scenarios. On the top of our framework is a toy graph vector library that we established, which captures key attributes, such as features and task-specific label information. During inference, the RAGRAPH adeptly retrieves similar toy graphs based on key similarities in downstream tasks, integrating the retrieved data to enrich the learning context via the message-passing prompting mechanism. Our extensive experimental evaluations demonstrate that RAGRAPH significantly outperforms state-of-the-art graph learning methods in multiple tasks such as node classification, link prediction, and graph classification across both dynamic and static datasets. Furthermore, extensive testing confirms that RAGRAPH consistently maintains high performance without the need for task-specific fine-tuning, highlighting its adaptability, robustness, and broad applicability. © 2024, CC BY-NC-ND.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutual Information

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutua...

引用

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

作者： Jicun Li Xingjian Li Tianyang Wang Shi Wang Yanan Cao Chengzhong Xu Dejing Dou Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Big Data Lab Baidu Research State Key Lab of IOTSC University of Macau University of Alabama at Birmingham Institute of Information Engineering Chinese Academy of Sciences

Fine-tuning pre-trained language models, such as BERT, has shown enormous success among various NLP tasks. Though simple and effective, the process of fine-tuning has been found unstable, which often leads to unexpected poor performance. To increase stability and generalizability, most existing works resort to maintaining the parameters or representations of pre-trained models during fine-tuning. Nevertheless, very little work explores mining the reliable part of pre-learned information that can help to stabilize fine-tuning. To address this challenge, we introduce a novel solution in which we fine-tune BERT with stabilized cross-layer mutual information. Our method aims to preserve the reliable behaviors of cross-layer information propagation, instead of preserving the information itself, of the pre-trained model. Therefore, our method circumvents the domain conflicts between pre-trained and target tasks. We conduct extensive experiments with popular pre-trained BERT variants on NLP datasets, demonstrating the universal effectiveness and robustness of our method.

关键词： Cross layer design Bit error rate Signal processing Stability analysis Robustness Acoustics Behavioral sciences

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：