检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Yin, Zhaoxia Yin, Heng Zhang, Xinpeng School of Communication and Electronic Engineering East China Normal University Shanghai China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University China School of Computer Science and Technology Fudan University Shanghai China

Deep neural networks are vulnerable to malicious fine-tuning attacks such as data poisoning and backdoor attacks. Therefore, in recent research, it is proposed how to detect malicious fine-tuning of neural network models. However, it usually negatively affects the performance of the protected model. Thus, we propose a novel neural network fragile watermarking with no model performance degradation. In the process of watermarking, we train a generative model with the specific loss function and secret key to generate triggers that are sensitive to the fine-tuning of the target classifier. In the process of verifying, we adopt the watermarked classifier to get labels of each fragile trigger. Then, malicious fine-tuning can be detected by comparing secret keys and labels. Experiments on classic datasets and classifiers show that the proposed method can effectively detect model malicious fine-tuning with no model performance degradation. Copyright © 2022, 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

Boosting performance of virtualized desktop infrastructure with physical GPU and SPICE

引用

Science China(Information Sciences) 2020年第7期63卷 236-238页

作者： Shupan LI Limin XIAO Chungang SHI Liequan CHE Changyou ZHANG Yuanzhang LI State Key Laboratory of Software Development Environment Beihang University School of Computer Science and Engineering Beihang University Beijing Jinghang Computation and Communication Research Institute Institute of Software Chinese Academy of Sciences School of Computer Science and Technology Beijing Institute of Technology

Dear editor,The virtual desktop infrastructure (VDI) is widely used by enterprises, as it can be easily deployed,has a reduced management cost, improves resource utilization, and can be accessed at any location by the network. Currently, there is a demand for the VDIs to support applications, such as playing 3D games, playing HD videos, and using 3D design-

关键词： visualized desktop infrastructure SPICE physical GPU The virtual machine (VM) virtual machine monitor (VMM)

来源：评论

学校读者我要写书评

暂无评论

Decision-Based Iterative Fragile Watermarking for Model Integrity Verification

SSRN

引用

SSRN 2023年

作者： Yin, Zhaoxia Yin, Heng Su, Hang Zhang, Xinpeng Gao, Zhenzhe Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai Shanghai200241 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Anhui Hefei230000 China Department of Computer Science and Technology Tsinghua University Beijing Beijing100000 China School of Computer Science and Technology Fudan University Shanghai Shanghai200241 China School of Communication and Electronic Engineering East China Normal University Shanghai Shanghai200241 China

Foundation models are commonly hosted on cloud servers to cater to the high demand for their services. However, this exposes them to security risks, as attackers can manipulate these models by introducing backdoor patterns after uploading them to the cloud or during transfer from a local *** mitigate this issue, we propose an iterative decision-based fragile watermarking algorithm to verify the integrity of remote models. This algorithm transforms normal training samples into fragile samples that exhibit sensitivity to model changes. During validation, we compare the output of sensitive samples from the original model to that of the compromised model, enabling us to assess the completeness of the *** method offers several advantages: Firstly, the iterative update of samples occurs in a decision-based black-box manner, relying solely on the predicted probability distribution of the target model. This approach reduces the risk of exposure to adversarial attacks. Secondly, even with changes in the overall parameters of the model at a magnitude of 1e-4, the fragile samples can detect such changes. Lastly, our method is independent of the specific *** experiments demonstrate the effectiveness of our proposed method on various models and datasets, highlighting its superior performance compared to the current state-of-the-art techniques. © 2023, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Talking Head Generation for Media Interaction System with Feature Disentanglement

Talking Head Generation for Media Interaction System with Fe...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Lei Zhang Qingyang Chen Zhilei Liu College of Intelligence and Computing School of New Media and Communication Tianjin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun P.R. China State Key Laboratory for Novel Software Technology Nanjing University P.R. China School of New Media and Communication Tianjin University Tianjin China College of Intelligence and Computing Tianjin University Tianjin China

The task of talking head generation for the media interaction system is to take images and audio clips of the target face as input, and generate a realistic video of the target synchronized with the audio. Most of the existing works directly take all the information in the image as input, which causes the problem of feature information redundancy. At the same time, in the stage of feature fusion, the image and audio information is directly spliced, and the relationship between the two modal information is ignored. To solve the problems, we initially implement the disentanglement of image by introducing a loss function to separate the image into identity features and content-related features. Besides, we introduce a multi-head selfattention mechanism to learn the relationship between the two modal information of image and audio, and implement the full fusion of multi-modal information. In addition, we validate the effectiveness of our model through extensive quantitative and qualitative analysis of two datasets. Extensive experiments show the superiority of the proposed model in all aspects.

关键词： Analytical models Redundancy Media Synchronization Task analysis Faces

来源：评论

学校读者我要写书评

暂无评论

Physical Layer Encryption Scheme Based on Population Evolution Iteration and Nonlinear Companding in CO-OFDM System 12

Physical Layer Encryption Scheme Based on Population Evoluti...

引用

12th IEEE International Conference on Electronics Information and Emergency communication, ICEIEC 2022

作者： Xu, Zeyu Huang, Hongbing Wang, Hongyan He, Chen Zhang, MingXi Yang, Changqing Chen, Julong Xu, Mengjie Zhan, Peng Tang, Xianfeng Beijing University of Posts and Telecommunications State Key Laboratory of Information Photonics and Optical Communications Beijing100876 China State Grid Zhejiang Electric Power Corporation Information & Telecommunication Branch Zhejiang310000 China Anhui Jiyuan Software Co. Ltd Sgitg Hefei230088 China Information and Communication Branch of Hubei Electric Power Company Hubei430000 China

ISBN: (数字)9781665407540

ISBN: (纸本)9781665407540

A physical layer encryption scheme based on population evolution iteration (PEI) and nonlinear companding is proposed to improve the security and reduce peak-to-average power ratio of the coherent optical orthogonal frequency division multiplexing (CO-OFDM) system. Simulation conducted in a 28Gbaud 16QAM system proves that the scheme can reduce the PAPR by 4dB, while the bit error rate of eavesdropper is about 0.5, which indicates that the scheme can guarantee the security on the premise of ensuring efficient transmission. © 2022 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Improved accuracy of PMD measurement based on spectral periodic interference 20

Improved accuracy of PMD measurement based on spectral perio...

引用

20th International Conference on Optical communications and Networks, ICOCN 2022

作者： Gao, Chuanwei Huang, Hongbing Zhang, Yi Li, Yinyi Wang, Hongyan Zhan, Peng An, Ning Tang, Xianfeng Beijing University of Posts and Telecommunications State Key Laboratory of Information Photonics and Optical Communications Beijing China State Grid Zhejiang Electric Power Corporation Information and Telecommunication Branch Zhejiang China Anhui Jiyuan Software Co. Ltd HeFei China Information and Communication Branch of Hubei Electric Power Company HuBei China Northeast Branch of State Grid Corporation of China ShenYang China

ISBN: (数字)9781665458986

ISBN: (纸本)9781665458986

In this paper, we propose a calculation method which can improve the measurement accuracy of polarization mode dispersion (PMD) in optical fiber composite overhead ground wire (OPGW) by fixed analyzer method. The proposed method calculates the interference period from the optical spectrum and extends the number of extreme points to the decimal fraction, which increases the accuracy of estimation of mean differential group delay (DGD) by extrema density (ED) and will not impact on measurement time or instrument cost. The results of experiment show that the PMD values calculated by the proposed method are closer to those measured by the EXFO instrument than by the traditional method. © 2022 IEEE.

关键词： Polarization mode dispersion

来源：评论

学校读者我要写书评

暂无评论

A CPK-Based Identity Authentication Scheme for IoT

引用

Computer Systems Science & Engineering 2022年第3期40卷 1217-1231页

作者： Mingming Zhang Jiaming Mao Yuanyuan Ma Liangjie Xu Chuanjun Wang Ran Zhao Zhihao Li Lu Chen Wenbing Zhao State Grid Jiangsu Electric Power Co. Ltd.Information&Telecommunication BranchNanjing210008China State Grid Key Laboratory of Information&Network Security Institute of Information and CommunicationGlobal Energy Interconnection Research InstituteNanjing210003China Anhui Jiyuan Software Co.Ltd SGITGHefei230088China Engineering Research Center of Post Big Data Technology and Application of Jiangsu Province Research and Development Center of Post Industry Technology of the State Posts Bureau(Internet of Things Technology)Engineering Research Center of Broadband Wireless Communication Technology of the Ministry of EducationNanjing University of Posts and TelecommunicationsNanjing210003China Department of Electrical Engineering and Computer Science Cleveland State UniversityCleveland44115USA

As the power Internet of Things(IoT)enters the security construction stage,the massive use of perception layer devices urgently requires an identity authentication scheme that considers both security and *** existing public key infrastructure(PKI)-based security authentication scheme is currently difficult to apply in many terminals in *** key distribution and management costs are high,which hinders the development of power IoT security *** Public key(CPK)technology uses a small number of seeds to generate unlimited public *** is very suitable for identity authentication in the power Internet of *** this paper,we propose a novel identity authentication scheme for power *** scheme combines the physical unclonable function(PUF)with improved CPK technology to achieve mutual identity authentication between power IoT terminals and *** proposed scheme does not require third-party authentication and improves the security of identity authentication for power ***,the scheme reduces the resource consumption of power IoT *** improved CPK algorithm solves the key collision problem,and the third party only needs to save the private key and the public key *** results show that the amount of storage resources occupied in our scheme is *** proposed scheme is more suitable for the power IoT.

关键词： Power Internet of Things terminal equipment identity authentication CPK PUF

来源：评论

学校读者我要写书评

暂无评论

Diverse Co-saliency Feature Learning for Text-Based Person Retrieval

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5465-5477页

作者： You, Shuai Chen, Cuiqun Feng, Yujian Liu, Hai Ji, Yimu Ye, Mang Nanjing University of Posts and Telecommunications (NJUPT) School of Internet of Things Nanjing China Anhui University School of Computer Science and Technology Hefei China South China Normal University school of computer Guangdong China NJUPT School of Computer Science Nanjing China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan 430072 China

Text-based Person Retrieval (TPR) plays a pivotal role in video surveillance systems for safeguarding public safety. As a fine-grained retrieval task, TPR faces the significant challenge of precisely capturing highly discriminative features across image and text modalities. Existing methods primarily focus on establishing modality-shared feature spaces to bridge cross-modal discrepancies. However, these methods are prone to disturbances from irrelevant information, such as background noises in the visual modality, and often over-emphasize specific local regions while neglecting the capture of diverse discriminative modal features, thereby limiting the robustness of cross-modal matching. In this paper, we introduce a novel framework, termed the Diverse Co-saliency Feature Learning Network (DCFL), which mines the co-saliency information between image and text modalities and enhances the diversity of cross-modal discriminative features while mitigating the interference of noise. Specifically, to construct cross-modal co-saliency features, we devise the Intra-modal Saliency Feature Learning (ISFL) and Cross-modal Saliency Feature Matching (CSFM) modules. ISFL employs a weighted mask mechanism to guide the model in reducing the impact of noise information in both modalities. Complementing ISFL, CSFM establishes consistent relationships between saliency features across modalities, leveraging text descriptions to align pedestrian-relevant visual regions. Furthermore, we propose the Diverse Co-saliency Feature Mining (DCFM) to bolster the diversity of discriminative co-saliency features across both image and text modalities. This module integrates a diversity regularization term, enabling the extraction of varied visual cues and capturing comprehensive features of the target individual. Extensive benchmark experiments demonstrate a substantial superiority of our approach over the state-of-the-art methods. The code will be released publicly. © 2005-2012 IEEE.

关键词： Co-saliency features modeling Diverse Co-saliency features Mining Text-based person retrieval

来源：评论

学校读者我要写书评

暂无评论

An Authentication Mechanism for IoT Devices Based on Traceable and Revocable Identity-Based Encryption 7th

An Authentication Mechanism for IoT Devices Based on Tra...

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Xia, Fei Mao, Jiaming Shao, Zhipeng Xu, Liangjie Zhao, Ran Yang, Yunzhi State Grid Jiangsu Electric Power Co Ltd. Information and Telecommunication Branch Nanjing210024 China Institute of Information and Communication State Grid Key Laboratory of Information and Network Security Global Energy Interconnection Research Institute Nanjing Jiangsu210003 China Anhui Jiyuan Software Co. Ltd SGITG Hefei Anhui230088 China

ISBN: (纸本)9783030786113

To solve low computing efficiency and high computational energy consumption in the traditional Public-key Infrastructure cryptosystem in the authentication of IoT devices, an authentication scheme for IoT devices based on the Identity-based Encryption is proposed in this paper, which is realized by introducing traceable and revocable mechanisms. The effective management of the secret key of the suspicious devices by the authentication center and the reasonable accountability of the dishonest private key generator (PKG) are realized. Finally, through the security proof, it is verified that the Identity-based Encryption designed in this paper can meet the security of the Chosen Ciphertext Attack (CCA), indicating that the scheme has high practicability and security. © 2021, Springer Nature Switzerland AG.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

High Capacity Reversible Data Hiding in Encrypted 3D Mesh Models Based on Multi-MSB Prediction

arXiv

引用

arXiv 2021年

作者： Lyu, Wan-Li Cheng, Lulu Yin, Zhaoxia Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University 230601 China School of Communication & Electronic Engineering East China Normal University Shanghai200241 China

The interaction of massive data in the network world poses an enormous threat to data security. Reversible data hiding in encrypted domain (RDH-ED) technology ensures the security of data storage. Extensive works of RDH-ED take digital images as the cover mediums. With the advancement of multimedia technology, three-dimensional (3D) models are widely used on the network. In recent years, 3D models have also been used by researchers as cover mediums for RDH-ED technology. However, it is still challenging to improve the embedding rate under the premise of ensuring reversibility. This paper proposes an RDH-ED method to improve the embedding rate significantly, and the 3D mesh model can be restored after data extraction. Firstly, the vertices of the 3D mesh models are classified into "embedded set" and "prediction set" based on odd-even property of indices. Based on the high correlation of the two sets, multiple most significant bit (multi-MSB) prediction is adopted to calculate room redundancy. Arithmetic coding compresses auxiliary information generated during the reserved room phase to further free up space. In addition, the correlation between two sets is used to recover vertices that were modified due to data hiding. Experimental results show the proposed method greatly improves the embedding rate compared with state-of-the-art methods and guarantees model recovery with high quality. Copyright © 2021, The Authors. All rights reserved.

关键词： Forecasting

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：