检索结果-内蒙古大学图书馆

Efficient Adaptive lab.l Refinement for lab.l noise learning

Neurocomputing 2025年 639卷

作者： Zhang, Wenzhen Cheng, Debo Lu, Guangquan Zhou, Bo Li, Jiaye Zhang, Shichao School of Computer Science and Engineering Guangxi Normal University Guangxi Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guangxi Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guangxi Guilin541004 China School of Computer Science and Technology Hainan University Hainan Haikou570228 China Guangxi Collaborative Innovation Center of Modern Sericulture and Silk Hechi University Guangxi Hechi546300 China The State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou310027 China

Deep neural networks are highly susceptible to overfitting noisy lab.ls, which leads to degraded performance. Existing methods address this issue by employing complex manually designed strategies, aiming to achieve optimal partitioning in each iteration to avoid fitting noisy lab.ls while thoroughly learning clean samples. However, this often results in models that are overly sensitive to hyperparameters and challenging to train. To address this issue, we decouple the tasks of avoiding fitting incorrect lab.ls and thoroughly learning clean samples, proposing a simple yet highly applicable method called Adaptive lab.l Refinement (ALR). First, inspired by lab.l refurbishment techniques, we update the original hard lab.ls to soft lab.ls using the model's predictions to reduce the risk of fitting incorrect lab.ls. Then, by introducing entropy loss, the model adaptively ’harden’ the high-confidence soft lab.ls based on the confidence differences, guiding the model to focus more on learning from clean samples. This approach is simple and efficient, requiring no auxiliary datasets and minimal hyperparameter tuning, making it more adaptable than existing methods that require careful adjustments for different datasets. We validate ALR's effectiveness through experiments on benchmark datasets with artificial lab.l noise (CIFAR-10/100) and real-world datasets with inherent noise (ANIMAL-10N, Clothing1M, WebVision). The results show that ALR outperforms state-of-the-art methods. © 2025

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A resynchronization attack on stream ciphers filtered by Maiorana-McFarland functions

引用

Frontiers of computer Science 2011年第2期5卷 158-162页

作者： Wenfeng YANG Yupu HU Key Laboratory of Computer Networks and Information Security Ministry of Education Xidian University Xi＇an 710071 China

A resynchronization attack is proposed on stream ciphers filtered by Maiorana-McFarland （M-M） functions and equipped with a linear resynchronization mechanism. The proposed attack utilizes the linear weakness of the resynchronization mechanism, the partial linearity of M-M functions, and applies the linear consistency test method to recover the secret key. It is shown that an M-M function should not be implemented by itself but rather in combination with other nonlinear components in stream ciphers using linear mechanisms to prevent the proposed attack. It is also shown that the use of linear resynchronization mechanisms should be avoided despite their high efficiency in stream ciphers filtered by M-M functions.

关键词： stream ciphers Maiorana-McFarland (M-M) functions cryptanalysis resynchronization attack

来源：评论

学校读者我要写书评

暂无评论

Exploring Triple Knowledge Cues for Zero-Shot Human-Object Interaction Detection

Exploring Triple Knowledge Cues for Zero-Shot Human-Object I...

引用

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

作者： Fang Nan Ni Zhang Qidong Liu Wei Jing Guang Dai Yan Chen Feng Tian Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China School of Automation Northwestern Polytechnical University Xi’an China Lenovo Research Bei Jing China SGIT AI Lab State Grid Corporation of China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current zero-shot human-object interaction detection methods often follow a two-phase pipeline, which uses a pre-trained detector to detect instances and then adopts CLIP to perform interaction prediction. During the second phase, they either obtain pairwise representations by directly performing RoI-Align on CLIP features or designing additional queries and decoders to fuse CLIP features. However, CLIP visual features often lack fine-grained information, thus being detrimental to capturing complex HOI interactions. Besides, extra decoders might increase computation costs. Thus, we propose a triple knowledge cues exploration model without extra decoders to explore various knowledge guidance for improving CLIP representations. First, we incorporate position distribution and semantic priors to delineate a layout from the predicted boxes and inject semantics by using the CLIP text embeddings. Next, we explore object priors by leveraging predefined class names and the text encoder to obtain saliency maps for humans and objects. Then, we design three types of holistic tokens to capture diverse attribute cues for human, object, and interaction, respectively. The above cues are finally integrated into a vanilla two-stage CLIP-based baseline. The experimental results on HICO-DET demonstrate the effectiveness of our proposed model.

关键词： Visualization Costs Fuses Semantics Layout Pipelines Detectors Signal processing Decoding Speech processing

来源：评论

学校读者我要写书评

暂无评论

Cryptanalysis of PRIMATEs

引用

Science China(information Sciences) 2020年第1期63卷 130-139页

作者： Yanbin LI Meiqin WANG Wenqing LIU Wei WANG Key Laboratory of Cryptologic Technology and Information Security Ministry of EducationShandong University Shandong Provincial Key Laboratory of Computer Networks

PRIMATEs is a family of authenticated encryption design submitted to competition for authenticated encryption: security, applicability, and robustness. The three modes of operation in PRIMATEs family are: APE, HANUMAN, GIBBON with security levels: 80, 120 bits. APE is robust despite the nonce misusing. In this study, we revise the algebraic model and find new integral distinguishers for both PRIMATE permutation and its inverse permutation. Moreover, we construct a zero-sum distinguisher for full12-round PRIMATE-80/120 permutation with the 2;/2;complexity, improving over previous work. We also perform an integral attack on 8-round finalization of APE-80/120 with 2;chosen messages. The key recovery process is optimized using the FFT technique presented by Todo and Aoki. Our work is the best attack against APE, demonstrating the practical attack on 8-round finalization of APE-80. The new integral distinguishers apply to create forgeries on 5/6-round finalization of APE and HANUMAN that require2;/2;chosen messages, which is the first forgery attack against APE and HANUMAN.

关键词： PRIMATEs APE HANUMAN integral distinguisher key recovery attack forgery

来源：评论

学校读者我要写书评

暂无评论

ID-based Signcryption KEM to Multiple Recipients

引用

电子学报(英文版) 2011年第2期20卷 317-322页

作者： SUN Yinxia LI Hui Key Laboratory of Computer Networks and Information Security Ministry of Education Xidian University Xi＇an 710071 China

ID-based Signcryption K EM to M ultiple SUN Yinxia and LI Hui (key lab.ratory of computer networks and information security,ministry education,Xidian University,x an ***) Abstract-Identity based signcryption K ey encapsulattio mechanism (KEM)is used to encapsulate a sym- etric key during the c0nstruction of hybrid signcrypti0n in the identity based setting.W le introduce the notion of Identity based signcryption KEM to multiple recipients (mIDSC-KEM ).

关键词：收件人签密随机预言模型对称密钥封装机制安全模型双线性 GAP Identity based signcryption KEM, Multiple recipients, Indistinguishability, Unforgeability, Random oracle model, Gap bilinear Diffie-Hellman (Gap- BDH), Computational Diflle-Hellman (CDH).

来源：评论

学校读者我要写书评

暂无评论

Semantic and Emotional Dual Channel for Emotion Recognition in Conversation

引用

IEEE Transactions on Affective Computing 2025年

作者： Yang, Zhenyu Zhang, Zhibo Cheng, Yuhu Zhang, Tong Wang, Xuesong Jinan250353 China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250353 China China University of Mining and Technology Engineering Research Center of Intelligent Control for Underground Space Ministry of Education Xuzhou Key Laboratory of Artificial Intelligence and Big Data School of Information and Control Engineering Xuzhou221116 China South China University of Technology Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information School of Computer Science and Engineering Guangzhou510006 China Pazhou Lab Guangzhou510335 China Engineering Research Center Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou China

Emotion recognition in conversation (ERC) aims at accurately identifying emotional states expressed in conversational content. Existing ERC methods, although relying on semantic understanding, often encounter challenges when confronted with incomplete or misleading semantic information. In addition, when dealing with the interaction between emotional and semantic information, existing methods are often difficult to effectively distinguish the complex relationship between the two, which affects the accuracy of emotion recognition. To address the problems of semantic misdirection and emotional cross-talk encountered by traditional models when confronted with complex conversational data, we propose a semantic and emotional dual channel (SEDC) strategy for emotion recognition in conversations to process emotional and semantic information independently. Under this strategy, emotion information provides an auxiliary recognition function when the semantics are unclear or lacking, enhancing the accuracy of the model. Our model consists of two modules: the emotion processing module accurately captures the emotional features of each utterance through contrastive learning, and then constructs a dialogue emotion propagation map to simulate the emotional information conveyed in the dialogue;the semantic processing module combines an external knowledge base to enhance the semantic expression of the dialogue through knowledge enhancement strategies. This divide-and-conquer approach allows us to more deeply analyze the emotional and semantic dimensions of complex dialogues. Experimental results on the IEMOCAP, EmoryNLP, MELD, and DailyDialog datasets show that our approach significantly outperforms existing techniques and effectively improves the accuracy of dialogue emotion recognition. Our code is availab.e at https://***/r/SEDC-FCF1. © 2010-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Efficient quantum secret sharing scheme with two-particle entangled states

引用

Chinese Physics B 2011年第4期20卷 59-64页

作者：朱珍超张玉清付安民 Key Lab of Computer Networks and Information Security of Ministry of Education Xidian University National Computer Network Intrusion Protection Center Graduate University of the Chinese Academy of Sciences

This paper proposes a protocol for multi-party quantum secret sharing utilizing four non-orthogonal two-particle entangled states following some ideas in the schemes proposed by Liu et al. （2006 Chin. Phys. Lett. 23 3148） and Zhang et al. （2009 Chin. Phys. B 18 2149） respectively. The theoretical efficiency for qubits of the new protocol is improved from 50% to approaching 100%. All the entangled states can be used for generating the private key except those used for the eavesdropping check. The validity of a probable attack called opaque cheat attack to this kind of protocols is considered in the paper for the first time.

关键词： quantum secret sharing quantum entanglement Bell state nonorthogonal base

来源：评论

学校读者我要写书评

暂无评论

Two-step transmission with artificial noise for secure wireless SIMO communications

引用

Science China(information Sciences) 2015年第4期58卷 115-127页

作者： WANG Bo MU PengCheng YANG PeiZhi YIN QinYe Ministry of Education Key Lab for Intelligent Networks and Network Security School of Electronic and Information Engineering Xi’an Jiaotong University

The issue of physical layer security of the wireless single-input multiple-output(SIMO) system is addressed in this paper. We propose a two-step transmission scheme with artificial noise to improve the security and the scheme does not require the channel state information of the eavesdropper. In the first step, the destination which has multiple antennas generates a random reference symbol and artificial noise and transmits them in the direction of the source and its orthogonal space, respectively. The reference symbol is received by the source without being polluted by the artificial noise, while it is jammed by the artificial noise for the eavesdropper. In the second step, the symbol of the source is multiplied by the received reference symbol and then transmitted. Finally, the destination can directly estimate the symbol of the source using the reference symbol. However, the eavesdropper needs to additionally estimate the reference symbol for demodulating the symbol of the source, which usually obtains an inaccurate result due to the artificial noise. The informationtheoretic security of our scheme is analyzed and a lower bound of the achievable secrecy rate is derived. The performance of the new scheme is compared with that of the traditional approach under different input signals through numerical simulations. The results show that the proposed scheme outperforms the traditional SIMO approach especially in the high SNR region.

关键词： wireless communication physical layer security multi-antenna SIMO artificial noise

来源：评论

学校读者我要写书评

暂无评论

A 3D Memristive Cubic Map with Dual Discrete Memristors: Design, Implementation, and Application in Image Encryption

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Gao, Suo Iu, Herbert Ho-Ching Erkan, Ugur Simsek, Cemaleddin Toktas, Abdurrahim Cao, Yinghong Wu, Rui Mou, Jun Li, Qi Wang, Chunpeng Dalian Polytechnic University School of Information Science and Engineering Dalian116034 China The University of Western Australia School of Electrical Electronic and Computer Engineering Perth6009 Australia Faculty of Engineering Electrical and Electronics Engineering Respectively Karamanoglu Mehmetbey University Karaman70200 Turkey Ankara University Engineering Faculty Department of Artificial Intelligence and Data Engineering Ankara06830 Turkey Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan250000 China

Discrete chaotic systems based on memristors exhibit excellent dynamical properties and are more straightforward to implement in hardware, making them highly suitable for generating cryptographic keystreams. However, most existing memristor-based chaotic systems rely on a single memristor. This paper introduces a novel discrete chaotic system employing dual memristors, named the 3D memristive cubic map with dual discrete memristors (3D-MCM). The 3D-MCM system demonstrates richer and more intricate dynamical behaviors compared to its single-memristor counterparts, as verified through bifurcation diagrams, Lyapunov exponent spectra, and complexity analyses. Notably, the system exhibits coexisting attractors, substantially enhancing its dynamical complexity. Hardware implementation of the 3D-MCM attractors confirms its feasibility for industrial applications. To illustrate the system's potential in encryption tasks, this study integrates the quaternary-based permutation and dynamic emanating diffusion (QPDED-IE) scheme for image encryption with the *** results demonstrate that the QPDED-IE scheme based on the 3D-MCM exhibits strong diffusion and confusion properties, effectively resisting cryptanalytic attacks. © 1991-2012 IEEE.

关键词： Bifurcation (mathematics)

来源：评论

学校读者我要写书评

暂无评论

On the Joint Nonlinear Span of Multiple Binary Sequence

引用

电子学报(英文版) 2007年第2期16卷 321-325页

作者： DONG Lihua HU Yupu The Key Laboratory of Computer Networks and Information Security the Ministry of Education Xidian University Xi＇an 710071 China

Recent developments in stream ciphers show strong interests in word-based (or vectorized) stream ciphers. The theory of such stream ciphers required the study of the complexity of multisequences. In this paper the problem proposed by Rizomiliotis of determining the joint nonlinear span of the prescribed multiple sequences is considered for the first time. An efficient algorithm is proposed, by using the special block structure of the associated system of linear equations. Both the total processing time and the memory requirements are linear in the sequence length.

关键词：非线性区间二进制多序列密码学流密码

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：