检索结果-内蒙古大学图书馆

AdaptFRCNet: Semi-supervised adaptation of pre-trained model with frequency and region consistency for medical image segmentation

引用

Medical Image Analysis 2025年 103卷

作者： Along He Yanlin Wu Zhihong Wang Tao Li Huazhu Fu College of Computer Science Tianjin Key Laboratory of Network and Data Security Technology Nankai University Tianjin 300350 China Haihe Lab of ITAI Tianjin 300459 China Institute of High Performance Computing (IHPC) Agency for Science Technology and Research (A*STAR) 138632 Singapore

Recently, large pre-trained models (LPM) have achieved great success, which provides rich feature representation for downstream tasks. Pre-training and then fine-tuning is an effective way to utilize LPM. However, the application of LPM in the medical domain is hindered by the presence of a large number of parameters and a limited amount of labeled data. In clinical practice, there exists a substantial amount of unlabeled data that remains underutilized. Semi-supervised learning emerges as a promising approach to harnessing these unlabeled data effectively. In this paper, we propose semi-supervised adaptation of pre-trained model with frequency and region consistency (AdaptFRCNet) for medical image segmentation. Specifically, the pre-trained model is frozen and the proposed lightweight attention-based adapters (Att_Adapter) are inserted into the frozen backbone for parameter-efficient fine-tuning (PEFT). We propose two consistency regularization strategies for semi-supervised learning: frequency domain consistency (FDC) and multi-granularity region similarity consistency (MRSC). FDC aids in learning features within the frequency domain, and MRSC aims to achieve multiple region-level feature consistencies, capturing local context information effectively. By leveraging the proposed Att_Adapter along with FDC and MRSC, we can effectively and efficiently harness the powerful feature representation capability of the LPM. We conduct extensive experiments on three medical image segmentation datasets, demonstrating significant performance improvements over other state-of-the-art methods. The code is available at https://***/NKUhealong/AdaptFRCNet .

关键词：

来源：评论

学校读者我要写书评

暂无评论

PosFuzz:augmenting greybox fuzzing with effective position distribution

引用

Cybersecurity 2023年第4期6卷 123-143页

作者： Yanyan Zou Wei Zou JiaCheng Zhao Nanyu Zhong Yu Zhang Ji Shi Wei Huo Institute of Information Engineering Chinese Academy of SciencesBeijingChina School of Cyber Security University of Chinese Academy of SciencesBeijingChina State Key Lab of Processors Institute of Computing TechnologyChinese Academy of SciencesBeijingChina Key Laboratory of Network Assessment Technology Chinese Academy of SciencesBeijingChina Beijing Key Laboratory of Network Security and Protection Technology BeijingChina Zhongguancun Laboratory BeijingChina

Mutation-based greybox fuzzing has been one of the most prevalent techniques for security vulnerability discovery and a great deal of research work has been proposed to improve both its efficiency and ***-based greybox fuzzing generates input cases by mutating the input seed,i.e.,applying a sequence of mutation operators to randomly selected mutation positions of the ***,existing fruitful research work focuses on scheduling mutation operators,leaving the schedule of mutation positions as an overlooked aspect of fuzzing *** paper proposes a novel greybox fuzzing method,PosFuzz,that statistically schedules mutation positions based on their historical *** makes use of a concept of effective position distribution to represent the semantics of the input and to guide the *** first utilizes Good-Turing frequency estimation to calculate an effective position distribution for each mutation *** then leverages two sampling methods in different mutating stages to select the positions from the *** have implemented PosFuzz on top of AFL,AFLFast and MOPT,called Pos-AFL,-AFLFast and-MOPT respectively,and evaluated them on the UNIFUZZ benchmark(20 widely used open source programs)and LAVA-M *** result shows that,under the same testing time budget,the Pos-AFL,-AFLFast and-MOPT outperform their counterparts in code coverage and vulnerability discovery *** with AFL,AFLFast,and MOPT,PosFuzz gets 21%more edge coverage and finds 133%more paths on *** also triggers 275%more unique bugs on average.

关键词： Greybox fuzzing Mutation position Mutation operator Code coverage Vulnerability discovery

来源：评论

学校读者我要写书评

暂无评论

A prior embedding-driven architecture for long distance blind iris recognition

引用

Biomedical Signal Processing and Control 2025年 109卷

作者： Qi Xiong Xinman Zhang Jun Shen International College Hunan University of Arts and Sciences Changde 415000 China School of Automation Science and Engineering Faculty of Electronic and Information Engineering MOE Key Lab for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an 710049 Shaanxi China School of Computing and Information Technology University of Wollongong Wollongong NSW 2522 Australia

Blind iris images, caused by unknown degradation during the process of iris recognition at long distances, often lead to decreased iris recognition rates. Currently, limited literature addresses this issue. To tackle this challenge, we propose a prior embedding-driven architecture for long-distance blind iris recognition. Our approach introduces a blind iris image restoration network named Iris-PPRGAN. To effectively restore the texture of blind iris images, Iris-PPRGAN incorporates a Generative Adversarial network (GAN) as a Prior Decoder and a Deep Neural network (DNN) as the encoder. To enhance iris feature extraction, we also developed a robust iris classifier by modifying the bottleneck module of InsightFace, referred to as Insight-Iris. Initially, a low-quality blind iris image is restored using Iris-PPRGAN, and the restored image is subsequently recognized through Insight-Iris. Experimental results on the public CASIA-Iris-distance dataset demonstrate that our method outperforms state-of-the-art blind iris restoration techniques. Specifically, the recognition rate for long-distance blind iris images improves from 80.77 % (without restoration) to 90.38 % after applying our method, reflecting an approximate ten-percentage-point improvement. These results, validated both quantitatively and qualitatively, underscore the effectiveness of our approach in addressing the challenges of long-distance blind iris recognition.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Distributed energy balanced routing for wireless sensor network using energy prediction metric

Distributed energy balanced routing for wireless sensor netw...

引用

International Conference on Information Science and Control Engineering

作者： Quan Guo Xiaoying Song Liaoning Key Lab of Network Security and Computing Technology Dalian Neusoft Information Institute College of Computer Science and Engineering Northeastern University

ISBN: (纸本)9781509025367

A considerable amount of energy efficient routing algorithms have been proposed to save energy and prolong network lifetime. Those algorithms mainly focus on forwarding packets along the minimum energy path to the sink to merely minimize energy consumption, which causes an unbalanced distribution of residual energy among sensor nodes, and eventually results in a network partition. In this paper, we propose a distributed energy balanced routing algorithm using energy prediction metric (EBEP). The routing scheme considers not only efficient energy but also energy balance. Firstly, with the help of Markov chain model and state conversion model, the future residual energy of front neighbor nodes can be predicted so that it is the most important local information when a node makes routing decision. Furthermore, the function of cost is adopted by our EBEP routing algorithm in order to synthetically evaluate and then select the best candidate of next step. Finally, the experimental results demonstrate the performance advantages of our EBEP routing algorithm.

关键词： Wireless sensor networks Balancing energy consumption Energy-efficient routing Markov chain model Residual energy

来源：评论

学校读者我要写书评

暂无评论

Energy-balanced clustering routing protocol based on task separation in wireless sensor networks

Energy-balanced clustering routing protocol based on task se...

引用

International Conference on BioMedical Engineering and Informatics (BMEI)

作者： Wei Sun Xiaoying Song Fasheng Wang Software Center Northeastern University Shenyang China Liaoning Key Lab of Network Security and Computing Technology Dalian Neusoft University Information Dalian China

Clustering protocol for data gathering is one of the effective ways to solve the energy hole problem in wireless sensor networks. However, most of the existing clustering protocols focus on the network model with uniform node distribution. They cannot effectively apply to the real network where the sensor nodes are randomly non-uniformly deployed. In this paper, we propose an energy-balanced clustering routing protocol (EBCRP) based on task separation. In this scheme, the network is firstly divided into clusters by using global information. And each of them has the same number of sensor nodes in order to balance the energy consumption of intra-cluster. In succession, task separation, the tasks of traditional single cluster head are separated and achieved by two cluster heads respectively, is proposed to reduce the traffic burden for single cluster head. Then, we explore an energy-efficient and reliable inter-cluster routing algorithm, which considers comprehensively three factors: residual energy, distance and available buffer space of nodes. Simulation results and performance evaluation of EBCRP show significant improvement in network lifetime and energy balance.

关键词： Energy consumption Protocols Head Clustering algorithms Routing Algorithm design and analysis Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding Simultaneously Using Substitution of MSB and Compression of LSB of Encrypted Image 14

Reversible Data Hiding Simultaneously Using Substitution of ...

引用

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Sui, Liansheng Liu, Jie Cheng, Ying Xiao, Zhaolin Tian, Ailing School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an710048 China Student’s Affairs Division Xi’an University of Technology Xi’an710048 China Shaanxi Province Key Lab of Thin Film Technology and Optical Test Xi’an Technological University Xi’an710048 China

ISBN: (纸本)9781510657564

With the development of privacy protection, reversible data hiding methods in encrypted image have drawn extensive research interest. Among them, a new method is proposed based on embedding prediction errors, i.e., EPE-based method, where secret information is embedded in the encrypted most significant bit plane. Not only the original image can be recovered with high quality but also the payload can reach close to 1 bit per pixel (bpp). However, there are potential errors in the process of extracting secret data, because most significant bits of a part of pixels are used as flags to mark prediction error location. In this paper, a reversible data hiding method in encrypted image with high capacity is proposed by combining most significant bit prediction with least significant bit compression. At first, most significant bit of each pixel is predicted and a location map of prediction errors in the original image is generated. In the same time, the original image is encrypted using a stream cipher method. Then, the location map is embedded into the vacated space generated with compressing least significant bits and the secret data is embedded into most significant bits of a part of pixels without prediction errors. In this way, the marked encrypted image is obtained. Finally, the original image can be recovered without any error and the secret information can be extracted correctly from the marked encrypted image. Experimental results show that the proposed method has better performance than EPE-based and other methods. © 2022 SPIE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

AN ADULT SHORT MESSAGE RECOGNITION ALGORITHM BASED ON RESTRICTED CLOSE TEST OPTIMIZATION

AN ADULT SHORT MESSAGE RECOGNITION ALGORITHM BASED ON RESTRI...

引用

2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

作者： QIN-DONG SUN XIN-BO HUANG JIU-LONG ZHANG Network Computing and Security Tech.Key Lab.of Shaanxi Province Xi'an University of Technology Xi' College of Electronics and Information Xi'an Polytechnic University Xi'an 710048 China Network Computing and Security Tech.Key Lab.of Shaanxi Province Xi'an University of Technology Xi'

The flooding of adult short message has become an urgent problem of safety of message content. Existing researches on short message filtering pay much attention to rubbish and advertising short messages, and the granularity of categorization were too coarse. With an analysis of the characteristics of adult short messages, and considering the effectiveness and real time performance of filtering algorithm, this paper proposes an adult short message discriminating algorithm based on adultism-degree computation, and a threshold selecting algorithm based on close test optimization. Experiments show that the proposed algorithm can effectively discriminate adult short message with a 94.4％ correction rate, meanwhile it can meet the requirements of practical processing.

关键词： Content security Adult short message Content filtering Threshold selecting

来源：评论

学校读者我要写书评

暂无评论

Linear (k, n) Secret Sharing Scheme with Cheating Detection

Linear (k, n) Secret Sharing Scheme with Cheating Detection

引用

International Conference on Computer and Information technology (CIT)

作者： Yan-xiao Liu Zhi-xiao Wang Wen-yao Yan Shaanxi Key Lab for Network Computing and Security Xian University of Technology Xian China Xian Innovation College Yanan University Xian China

Linear (k,n) secret sharing scheme is a class of (k,n) secret sharing, where all the n shares of a secret satisfy a linear relationship. It plays an important role in other cryptographic systems, such as multi-party computation and function sharing schemes. On the other hand, cheating problem in (k,n) secret sharing is an important issue, such that cheaters (dishonest players) submit forged shares during secret reconstruction to fool honest players. During decades of research on cheating prevention, vast (k,n) secret sharing schemes against cheating have been proposed. However, most of these schemes are not linear schemes since it contains redundant information in their shares to achieve cheating detection. Since linear (k,n) secret sharing is an important primitive in threshold cryptography, linear (k,n) secret sharing scheme with the capability of cheating detection is also worthwhile to be discussed. In this paper, we propose a linear (k,n) secret sharing scheme against cheating based on Shamir's original scheme, which possesses the following merits: (1) Our scheme is just combination of two Shamir's schemes. Therefore, our scheme can be used in other threshold cryptographic systems which are based on Shamir's scheme. (2) The size of share in proposed scheme almost reaches its theoretic lower bound in (k,n) secret sharing with cheating detection. (3) In the phase of cheating detection, only one honest player can detect the cheating from other k-1 cheaters, which achieves a stronger detection effective than the previous linear secret sharing schemes against cheating.

关键词： Cryptography Information rates Conferences Computers Information technology Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Addressing the energy hole problem based on heterogeneous clustering size for wireless sensor networks

引用

Journal of Computational Information Systems 2014年第9期10卷 3973-3980页

作者： Song, Xiaoying Wen, Tao Guo, Quan Ma, Fengming Zhang, Dongqing Software Center Northeastern University Shenyang 110819 China Liaoning Key Lab. of Network Security and Computing Technology Dalian Neusoft Information Institute Dalian 116023 China School of Management Science Qufu Normal University Rizhao Shandong 276800 China

Clustering is one of the effective ways to solve energy hole problem for Wireless Sensor network. So far, the approaches of heterogeneous cluster size mainly have concentrated on the design of unequal cluster protocol rather than the optimal cluster radius theoretically. Furthermore, the existing protocols of data gathering fall short in the extra energy dissipation of the rotating cluster head frequently. To overcome these limitations, in this paper, we first present the theoretical analysis to obtain the optimal number of cluster when the energy dissipation is balancing in the whole network. Then, the optimal cluster radius of different rings is obtained by theoretical analysis as well. In succession, a simple and effective strategy is proposed to further prolong the network lifetime on basis of the optimal cluster radius obtained theoretically. Finally, the simulation results demonstrate the performance advantages of our approach. © 2014 Binary Information Press.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Modeling for user interaction by influence transfer effect in online social networks

Modeling for user interaction by influence transfer effect i...

引用

Conference on Local Computer networks (LCN)

作者： Qindong Sun Nan Wang Yadong Zhou Hanqin Wang Liansheng Sui Shaanxi Key Laboratory of Network Computing and Security Xi'an University of Technology Xi'an China MOE KLINNS Lab Xi'an Jiaotong University Xi'an China

User interaction is one of the most important features of online social networks, and is the basis of research of user behavior analysis, information spreading model, etc. However, existing approaches focus on the interactions between adjacent nodes, which do not fully take the interactions and relationship between local region users into consideration as well as the details of interaction process. In this paper, we find that there exists influence transfer effect in the process of user interactions, and present a regional user interaction model to analyze and understand interactions between users in a local region by influence transfer effect. Based on real data from Sina Weibo, we validate the effectiveness of our model by the experiments of user type classification, influential user identification and zombie user identification in online social networks. The experimental results show that our model present better performance than the PageRank based method and machine learning method.

关键词： Analytical models Twitter Data models laboratories Educational institutions Learning systems

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：