检索结果-内蒙古大学图书馆

8th International Conference on Artificial Intelligence and security , ICAIS 2022

作者： Huang, Jie Li, Fengyong Zhang, Lei Qin, Chuan School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China College of Computer Science and Technology Shanghai University of Electric Power Shanghai200090 China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China Computer Science Department University of Victoria VictoriaBC Canada

ISBN: (纸本)9783031067631

This paper proposes a two-stage lossless robust watermarking scheme based on deep neural network. In the first stage, the encoder, noise layer and decoder network are combined to design an end-to-end network framework, which is used to train the input watermark information and cover image. In this framework, the encoder outputs a robust watermarked image whose visual quality is similar to the cover image, and the decoder can extract the embedded watermark information to evaluate robustness. In the second stage, by using reversible information hiding algorithm with extended prediction error, the auxiliary information that can recover the cover image is embedded into the robust watermarked image to ensure reversibility. If the watermarked image does not undergo attack processing, the hidden watermark information can not only be extracted, but also the cover image can be completely recovered. Even if the watermarked image does undergo attack processing, the embedded watermark information can also be extracted correctly because of the strong robustness in the first stage. Experimental results demonstrate the robustness of proposed scheme in terms of JPEG compression, gaussian filtering noise, rotation and shearing operations. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

AH-TDMA: An Adaptive Heterogeneous Tridiagonal Matrix Algorithm on the New Sunway Supercomputer

AH-TDMA: An Adaptive Heterogeneous Tridiagonal Matrix Algori...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Min Tian Qi Liu Yanlong Li Wei Du Zenghui Ren Yue Liu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan Key Laboratory of High Performance Computing Jinan Institute of Supercomputing Technology

The solution of tridiagonal linear systems is used in in various fields and plays a crucial role in numerical simulations. However, there is few efficient solver for tridiagonal linear systems on the new Sunway supercomputer. Based on a three-dimensional heat conduction problem, we propose an adaptive heterogeneous tridiagonal matrix algorithm (AH-TDMA). Our major innovations include: (1) To address computational hotspots within AH-TDMA, a multi-level parallel approach involving MPI+Athread has been adopted. (2) An adaptive data partitioning scheme has been set up to achieve load balance. (3) Employing direct memory access and establishing shared space between registers and main memory, instead of employing discrete memory access, is done to enhance memory access efficiency. (4) The optimization of the loop structure has been made in adjusting the sequencing of the dual-layered loops to reduce communication overhead. The experimental results show that, with one core group, the AH-TDMA achieves a speedup of 99.6 times for hotspot and total time speedup up to 59.4 times compared to the Parallel and Scalable Library for Tridiagonal Matrix Algorithm (PaScal TDMA). The AH-TDMA is scalable up to 2048 core groups, with a parallel efficiency of 69.2%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Topic Embedded Representation Enhanced Variational Wasserstein Autoencoder for Text Modeling 5

Topic Embedded Representation Enhanced Variational Wasserste...

引用

5th IEEE International Conference on Electronics Technology, ICET 2022

作者： Xiang, Zheng Liu, Xiaoming Yang, Guan Liu, Yang Zhongyuan University of Technology School of Computer Science Zhengzhou China Henan Key Laboratory on Public Opinion Intelligent Analysis Zhengzhou China Key Laboratory of text processing and image understanding Zhengzhou China Xidian University State Key Laboratory of Integrated Services Networks Xi'an China Shandong University Key Lab of Cryptologic Technology and Information Security Ministry of Education Xi'an China

ISBN: (纸本)9781665485081

Variational Autoencoder (VAE) is now popular in modeling and language generation tasks, which need to pay attention to the diversity of generation results. The existing models are insufficient in capturing the built-in relationships between topic representation and sequential words. At the same time, there is a massive contradiction between the commonly used simple Gaussian prior and the actual complex distribution of languages. To address the above problems, we introduce a hybrid Wasserstein Autoencoder (WAE) with Topic Embedded Representation (TER) for modeling. TER is obtained through an embedding-based topic model and can capture the dependencies and semantic similarities between topics and words. In this case, the learned latent variable has rich semantic knowledge with the help of TER and is easier to explain and control. Our experiments show that our method is competitive with other VAEs in modeling. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

FAST: a dual-tier few-shot learning paradigm for whole slide image classification 24

FAST: a dual-tier few-shot learning paradigm for whole slide...

引用

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

作者： Kexue Fu Xiaoyuan Luo Linhao Qu Shuo Wang Ying Xiong Ilias Maglogiannis Longxiang Gao Manning Wang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China and Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Digital Medical Research Center School of Basic Medical Sciences Fudan University and Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Fudan University University of Piraeus

ISBN: (纸本)9798331314385

The expensive fine-grained annotation and data scarcity have become the primary obstacles for the widespread adoption of deep learning-based Whole Slide Images (WSI) classification algorithms in clinical practice. Unlike few-shot learning methods in natural images that can leverage the labels of each image, existing few-shot WSI classification methods only utilize a small number of fine-grained labels or weakly supervised slide labels for training in order to avoid expensive fine-grained annotation. They lack sufficient mining of available WSIs, severely limiting WSI classification performance. To address the above issues, we propose a novel and efficient dual-tier few-shot learning paradigm for WSI classification, named FAST. FAST consists of a dual-level annotation strategy and a dual-branch classification framework. Firstly, to avoid expensive fine-grained annotation, we collect a very small number of WSIs at the slide level, and annotate an extremely small number of patches. Then, to fully mining the available WSIs, we use all the patches and available patch labels to build a cache branch, which utilizes the labeled patches to learn the labels of unlabeled patches and through knowledge retrieval for patch classification. In addition to the cache branch, we also construct a prior branch that includes learnable prompt vectors, using the text encoder of visual-language models for patch classification. Finally, we integrate the results from both branches to achieve WSI classification. Extensive experiments on binary and multi-class datasets demonstrate that our proposed method significantly surpasses existing few-shot classification methods and approaches the accuracy of fully supervised methods with only 0.22% annotation costs. All codes and models will be publicly available on https://***/fukexue/FAST.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Essential proteins identification based on weak consensus model and neighborhood aggregation centrality

Essential proteins identification based on weak consensus mo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhipeng Hu Gaoshi Li Jingli Wu Xinlong Luo Jiafei Liu Wei Peng Xiaoshu Zhu Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guilin China College of Computer Science and Engineering Guangxi Normal University Guilin China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China School of Computer and Information Security & School of Software Engineering Guilin University of Electronic Science and Technology Guilin China

Essential proteins play an essential role in cell survival and replication. Currently, more and more computational methods are developed to identify essential proteins, which overcome the time-consuming, costly and inefficient shortcomings with biological experimental methods. In order to improve the recognition rate, some new methods by fusing multiple features are developed, but they seldom consider the connection among features. After analyzing a large number of methods based on multi-feature fusion, a weak consensus model to fuse features is proposed in this paper. Then, this paper uses the weak consensus model to fuse protein-protein interaction network, gene expression data, and orthologous data, thus proposing a new method, WOL. Then experiments are performed on one *** dataset. The results show that compared with WDC, PeC, ION, JDC, NCCO and E_POC, WOL has a higher recognition rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Monocular Camera-Based Visual Truck Type Recognition

SSRN

引用

SSRN 2024年

作者： Luo, Haibo Ye, Huaisheng Feng, Chao Shi, Xin Xie, Guoqi School of Computer and Data Science Minjiang University Fuzhou350018 China College of Computer and Data Science Fuzhou University Fuzhou350018 China College of Network and Information Security Fujian Agriculture and Forestry University Fuzhou350018 China Key Laboratory for Embedded and Network Computing of Hunan Province College of Computer Science and Electronic Engineering Hunan University Changsha410082 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China

Truck overload and over-limit are the primary causes of infrastructure damage and traffic safety accidents. In the past 2 years, researchers have started to deploy intelligent Internet of Things system at the source of truck delivery to enforce permit control. Truck type recognition is the core of such a system. However, existing methods suffer from limitations such as low recognition accuracy, high costs, difficult maintenance, and the need for road surface modifications. This study proposes a monocular camera-based visual truck type recognition method. First, the optimized lightweight deep neural network based on machine vision is utilized to detect truckaxles and recognize wheel hub categories. Next, a tracking algorithm and the video streamcontext information are employed to complete the robust statistics of the axle by neighborhoodcounting. Finally, the proposed method further achieves truck type recognition by leveragingavailable prior knowledge. Experimental results demonstrate that this method exhibits superiortime efficiency compared with existing algorithms, and it reduces average processing time by92.37% to 96.24% while ensuring high accuracy. Moreover, the method has been deployed onembedded devices with low computing power to enable real-time operation onsite. © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Safe and Reliable Diffusion Models via Subspace Projection

arXiv

引用

arXiv 2025年

作者： Chen, Huiqiang Zhu, Tianqing Wang, Linlin Yu, Xin Gao, Longxiang Zhou, Wanlei Faculty of Data Science City University of Macau China School of Computer Science University of Queensland QLD Australia 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 Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such as copyrighted works or offensive images. While existing methods attempt to eliminate specific unwanted concepts, they often fail to ensure complete removal—allowing the concept to reappear in subtle forms. For instance, a model may successfully avoid generating images in Van Gogh’s style when explicitly prompted with "Van Gogh", yet still reproduce his signature artwork when given the prompt "Starry Night". In this paper, we propose SAFER, a novel and efficient approach for thoroughly removing target concepts from diffusion models. At a high level, SAFER is inspired by the observed low-dimensional structure of the text embedding space. The method first identifies a concept-specific subspace Sc associated with the target concept c. It then projects the prompt embeddings onto the complementary subspace of Sc, effectively erasing the concept from the generated images. Since concepts can be abstract and difficult to fully capture using natural language alone, we employ textual inversion to learn an optimized embedding of the target concept from a reference image. This enables more precise subspace estimation and enhances removal performance. Furthermore, we introduce a subspace expansion strategy to ensure comprehensive and robust concept erasure. Extensive experiments demonstrate that SAFER consistently and effectively erases unwanted concepts from diffusion models while preserving generation quality. © 2025, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Risk Modeling and Traceability of Boundary Attacks on Internet of Power Systems Based on Complex networks 9

Risk Modeling and Traceability of Boundary Attacks on Intern...

引用

9th IEEE International Conference on Data Science in Cyberspace, DSC 2024

作者： Li, Xin Qu, Zhaoyang Yu, Tong Xie, Ming Yu, Fu Ding, Wei Northeast Electric Power University School of Electrical Engineering Jilin132012 China People's Bank of China Qinghai Provincial Branch Xining810000 China China Southern Power Grid Guangxi Power Grid Co. Ltd. Research Institute Nanning530023 China China Guizhou Power Grid Co. Ltd. Bijie Power Supply Bureau Bijie551700 China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China

ISBN: (纸本)9798350391367

With the increasing intelligence of power IoT terminal devices, the massive volume of data transmission, and the widespread adoption of shared services, traditional terminal boundary security mechanisms are unable to keep up with the rapid development of network technologies and applications. Additionally, they fail to trace and source network attacks, leading to frequent organized and purposeful malicious attack incidents. To address these issues, this paper proposes a research method for risk modeling and traceability of boundary attacks on power IoT terminals based on complex networks. First, based on the node information of power IoT terminal devices and complex network theory, a terminal boundary attack network (TBAN) is established. Next, using indicators related to complex network theory, such as degree, in-degree, and out-degree, the terminal boundary attack network is analyzed. Furthermore, a staged TBAN is proposed to analyze the attack risks at different times. Then, combining causal theory, a method for tracing and sourcing terminal boundary attacks based on a causal Bayesian network is proposed to identify and trace malicious attacks. Finally, validation and testing analysis are conducted using the actual deployment of power IoT terminal devices. The proposed analysis method transforms the spatial characteristics of the power IoT terminal boundary into a temporally sequential TBAN, which not only visually reflects attack risks but also reveals the temporal relationships of terminal boundary attacks between lines. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Differential Cryptanalysis of Round-Reduced SPEEDY Family 18th

Differential Cryptanalysis of Round-Reduced SPEEDY Family

引用

18th International Conference on information security and Cryptology, Inscrypt 2022

作者： Yu, Qingyuan Jia, Keting Zou, Guangnan Zhang, Guoyan School of Cyber Science and Technology Shandong University Shandong Qingdao266237 China Institute for Network Sciences and Cyberspace BNRist Tsinghua University Beijing10084 China Department of Computer Sciences and Technology Tsinghua University Beijing10084 China Key Laboratory of Cryptologic Technology and Information Security Ministry of Education Shandong University Shandong Qingdao266237 China Zhongguancun Laboratory Beijing China Shandong Institute of Blockchain Shandong Jinan China

ISBN: (纸本)9783031265525

SPEEDY is a family of ultra low latency block ciphers proposed at TCHES 2021 by Leander et al. The standard version, SPEEDY-6-192 offers 128-bit security with high encryption speed in hardware. Differential cryptanalysis proposed in 1990 by Biham and Shamir is one of the most popular methods of cryptanalysis of block ciphers. It is usually the first choice to evaluate the security for designers when designing a new block cipher. The automatic search for various distinguishers based on SAT and MILP models etc. boosts the cryptanalysis of block ciphers. However, the performance of the automatic search is not always satisfactory, especially for searching long differential trails of block ciphers with large state sizes. Hence, we endeavor to accelerate the SAT-based automatic search model for differentials of SPEEDY. In this paper, we give a 3.5-round differential characteristic with the probability of $$2^{-104.83}$$ and a 4.5-round differential characteristic with the probability of $$2^{-150.15}$$. Furthermore, by balancing the key recovery and the differential distinguisher, we adjust the distinguisher to speed up filtering wrong pairs with some tricks. Finally we launch a valid 6-round attack for SPEEDY-7-192 with a complexity of $$2^{158.06}$$. We also propose a 5-round attack utilizing a 3.5-round differential distinguisher with the time complexity of $$2^{108.95}$$. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

NeuVSA: A Unified and Efficient Accelerator for Neural Vector Search

NeuVSA: A Unified and Efficient Accelerator for Neural Vecto...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Ziming Yuan Lei Dai Wen Li Jie Zhang Shengwen Liang Ying Wang Cheng Liu Huawei Li Xiaowei Li Jiafeng Guo Peng Wang Renhai Chen Gong Zhang State Key Lab of Processors Institute of Computing TechnologyCAS University of Chinese Academy of Sciences School of Computer and Information Technology Shanxi University School of Computer Science Peking University Zhongguancun National Laboratory Beijing Key Lab of Network Data Science and Technology Institute of Computing Technology CAS Huawei Technologies Co. Ltd. China

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Neural Vector Search (NVS) has exhibited superior search quality over traditional key-based strategies for information retrieval tasks. An effective NVS architecture requires high recall, low latency, and high throughput to enhance user experience and cost-efficiency. However, implementing NVS on existing neural network accelerators and vector search accelerators is sub-optimal due to the separation between the embedding stage and vector search stage at both algorithm and architecture levels. Fortunately, we unveil that Product Quantization (PQ) opens up an opportunity to break separation. However, existing PQ algorithms and accelerators still focus on either the embedding stage or the vector search stage, rather than both simultaneously. Simply combining existing solutions still follows the beaten track of separation and suffers from insufficient parallelization, frequent data access conflicts, and the absence of scheduling, thus failing to reach optimal recall, latency, and throughput. To this end, we propose a unified and efficient NVS accelerator dubbed NeuVSA based on algorithm and architecture co-design philosophy. Specifically, on the algorithm level, we propose a learned PQ-based unified NVS algorithm that consolidates two separate stages into the same computing and memory access paradigm. It integrates an end-to-end joint training strategy to learn the optimal codebook and index for enhanced recall and reduced PQ complexity, thus achieving smoother acceleration. On the architecture level, we customize a homogeneous NVS accelerator based on the unified NVS algorithm. Each sub-accelerator is optimized to exploit all parallelism exposed by unified NVS, incorporating a structured index assignment strategy and an elastic on-chip buffer to alleviate buffer conflicts for reduced latency. All sub-accelerators are coordinated using a hardware-aware scheduling strategy for boosted throughput. Experimental results show that the joint training strategy improves recall

关键词： Training Quantization (signal) Philosophical considerations Graphics processing units computer architecture Throughput Vectors User experience System-on-chip Indexes

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：