检索结果-内蒙古大学图书馆

Data science and Network security (ICDSNS), International Conference on

作者： Honglei Li Xinlong Zhao School of Cyberspace Security (School of Cryptology) Hainan University Haikou China Key Laboratory of Internet Information Retrieval of Hainan Province Haikou China School of computer science and technology Hainan University Haikou China

Membership inference attack (MIA) attempts to determine whether a particular data sample has participated in the training process of the target model, and is regarded as basic form of privacy breach in machine learning. This paper provides a label-only membership inference attack to well-generalized automatic speech recognition (ASR) systems, while only being granted black-box access permissions for the target system. Initially, we develop shadow models as substitution of the target ASR model. Subsequently, data augmentation techniques are employed to generate additional speech samples for the member and non-member sets elements of the shadow models. These augmentation techniques include modifying speech speed, cropping, adding noise, and so on. We query the shadow models with all the samples above, and we can derive a series of features from the model's output. All the features and their corresponding membership labels are then utilized to train an audit model. This audit model will be used to judge the membership of a given sample. The experimental results indicate that the performance metrics of this attack are significantly higher when the adversary has knowledge about the data distribution of target model's training set and the target model's architecture. However, if the adversary is lack of this knowledge, the probability of successful MIA is comparable to random guessing. The main contribution is that we investigate the membership leakage in well-generalized auto speech recognition system, and propose a data augmentation-based membership inference attack. We also discuss the transferability of the proposed scheme under various attack uncertainty.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Imagined Speech Production from Electrocorticography with Adaptive Frequency Enhancement

Robust Imagined Speech Production from Electrocorticography ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xu Xu Chong Fu Junxin Chen Gwanggil Jeon David Camacho School of Computer Science and Engineering Northeastern University Shenyang China School of Software Dalian University of Technology Dalian China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Engineering Research Center of Security Technology of Complex Network System Ministry of Education Shenyang China College of Information Technology Incheon National University Incheon Korea Department of Computer Systems Engineering Universidad Politécnica de Madrid Madrid Spain

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Imagined speech production with electrocorticography (ECoG) plays a crucial role in brain-computer interface system. A challenging issue is the great variation underlying the frequency bands of the ECoG signals’ encode information, which makes current methods difficult to generate imagined speech with stable quality among different persons. To this end, we propose a robust model to generate high-quality imagined speech from ECoG. A frequency enhancement branch is first designed to adaptively modulate the frequency information, whose product is fed into the following multi-scale channel attention module for robust feature extraction and fusion. By incorporating both the mel-spectrum and audio as training constraints, a multi-constraint decoder branch is finally constructed for imagined speech production. The performance of our model is evaluated on a high-quality dateset, i.e, Single Word Production Dutch-iBIDS. It yields Pearson correlation scores that are all above 0.8, and the standard deviationsare are all below 0.2 in different volunteers. Experimental results demonstrate that our model is effective and robust for ECoG based imagined speech production, and has advantages over peer methods.

关键词： Training Adaptation models Frequency modulation Correlation Neuroscience Production Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Syn-BERT: Bi-level Synonymous Data Augmented Self-supervised Embedding-based information Retrieval with BERT

Syn-BERT: Bi-level Synonymous Data Augmented Self-supervised...

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Zhaojian Yu Tianlin Huang Rong Chen Haosheng Chen Shuyuan Lin College of Cyber Security Jinan University Guangzhou China School of Mathematics and Computer Science Quanzhou Normal University Quanzhou China Information Engineering College Xizang Minzu University Shanyang China Chongqing Key Laboratory of Image Cognition College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (数字)9798350355925

ISBN: (纸本)9798350355932

information retrieval, which seeks to locate the most relevant documents from a document pool given a user query, is critical in a wide range of applications. However, current embedding-based retrieval models require a high quantity of labeled documents as training data to construct appropriate target training tasks, which can be expensive and difficult to obtain in practical applications. In this paper, we present a Synonymous BERT (Syn-BERT) model with strong training data augmentation with the aim of building an effective and efficient retrieval system on unlabeled documents. Unlike most existing embedding-based retrieval models, which require high-quality labeled documents to learn the semantic connections between original documents and labels, the proposed Syn-BERT generates synonymous queries and irrelevant queries for each original document in unlabeled documents and exploits the distances between them to obtain better embeddings. We evaluated the proposed Syn-BERT on two publicly-available Frequently Asked Question datasets, with the experimental results demonstrating that the proposed Syn-BERT achieved state-of-the-art results in embedding-based retrieval tasks with unlabeled documents.

关键词： Training Adaptation models Visualization Patents Semantics Training data Predictive models Data models Generators Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Effectiveness Evaluation for Clinical Depression Detection Using Deep Learning Based Synthetic House-Tree-Person Test

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Chen, Zhuolong Yin, Xiaoqing Yang, Fan Li, Xiaofan Zhao, Zixuan Li, Xueying Liu, Jianghu Zhao, Yubin Xu, Cheng-Zhong Zheng, Fangfang Lin, Yong Sun Yat-Sen University School of Microelectronics Science and Technology 0000 China The Fifth Affiliated Hospital of Sun Yat-Sen University Department of Psychiatry 0000 China The Fifth Affiliated Hospital of Sun Yat-Sen University Pediatrics Department 0000 China Jinan University School of Intelligent System Science and Engineering 0000 China University of Macau State Key Laboratory of IoTSC Department of Computer and Information Science Macau0000 China

Depression is one of the most common mood disorders and the number of patients increases significantly in recent years. Due to the lack of biomarkers, conversation between patients and psychiatrists is still the main clinical diagnostic method which is easily influenced by subjectivity of both patients and psychiatrists. Synthetic House-tree-person test (S-HTP), a convenient and efficient mental assessment tool, minimizes subjective influences from patients, while its effectiveness is limited by the professional ability of analyst. Here we introduce a deep learning model DeHTP, a flexible and convenient depression detection method based on S-HTP without interaction between people. Experimental results demonstrate that DeHTP achieves 0.963 AUC and 0.9 accuracy, and outperforms the conventional manual analysis of S-HTP, which is conducted on the guideline of 50 conclusions from previous study related to depression. In addition, it reveals 22 depression-correlated drawing features aligned with conclusions above from the perspective of our proposed model. Leveraging the advantages of deep learning and S-HTP, this approach has the potential for widespread promotion and adoption as the available tool for daily self-mental monitoring, as well as the promising auxiliary diagnostic method in clinical. © 2013 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Privacy-Preserving Data Sharing Scheme Supporting Intelligent Pricing in Smart Grid

A Lightweight Privacy-Preserving Data Sharing Scheme Support...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Xinyang Li Yujue Wang Yong Ding Yijie Zhou Changsong Yang Zhenwei Guo Guangxi Key Laboratory of Cryptography and Information Security School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Hangzhou Innovation Institute of Beihang University Hangzhou China Institute of Cyberspace Technology HKCT Institute for Higher Education Hong Kong China Guangxi Radio and Television Nanning China

ISBN: (数字)9798350358261

ISBN: (纸本)9798350358278

Smart grid is the future direction of the traditional power system, with characteristics such as high efficiency and stability. Intelligent pricing, as part of the functionality of smart grids, relies on collecting a large amount of user power data to analyze and adjust electricity prices, which may lead to the possibility of user privacy data leakage. To address these issues, we propose a privacy-preserving scheme for smart grids that supports intelligent pricing (PSR). A data aggregation mechanism is designed based on Paillier encryption and Schnorr signature technology, which can protect the privacy of user data and realize efficient aggregation of user power data in the control center. In addition, a proxy re-encryption technology is developed to enable secure sharing of user power data between users and service providers. Based on security analysis and experimental evaluations, the PSR scheme has stronger security and higher efficiency compared to existing schemes.

关键词： Data privacy Electricity Pricing Data aggregation Power system stability Stability analysis Smart grids

来源：评论

学校读者我要写书评

暂无评论

MineLoRa: Markov Transition Fields and Adaptive Neural Networks for LoRa Device Radio Frequency Fingerprint Identification

MineLoRa: Markov Transition Fields and Adaptive Neural Netwo...

引用

Artificial Intelligence of Things and systems (AIoTSys), International Conference on

作者： Biaokai Zhu Yupeng Jia Zhonghao Wang Jiawei Wen Xinle Liu Shijia Zhao Qiongyue Xu Jie Song Ping Li Sanman Liu Feng Li Jumin Zhao Shanxi Police College Taiyuan University of Technology Taiyuan China Cyber Security Department Shanxi Police College Taiyuan China Intelligent Policing Key Laboratory of Sichuan Province Sichuan Police College Luzhou China School of Computer Science and Technology Anhui University Hefei China Taiyuan University of Technology Taiyuan China College of Information and Computer Taiyuan University of Technology Jinzhong China

ISBN: (数字)9798331507886

ISBN: (纸本)9798331507893

With the development of LPWAN technology, LoRa, one of the typical representatives, is widely used in various communication scenarios. At the same time, it is also faced with problems such as difficulty in identifying the terminal equipment and the easy mistake and confusion. The industry has widely valued LoRa RF fingerprint recognition technology, which has become a security focus that cannot be ignored. Most recent research on terminal recognition has been carried out by multi-class feature fusion. Still, it needs help with high computational complexity, significant noise and other external interference factors, and harrowing feature extraction. We propose a time-frequency feature analysis method based on GAF and MTF. The time-domain features are transformed into two-dimensional images using the Gram Angle field and Markov transfer field. The spectral graph has both time-domain and frequency-domain characteristics, and the feature probability distribution in the images is intuitively analyzed. Finally, we design a deep neural network model based on CNN improvement. It can accurately extract and classify the features contained in multi-time frequency. Our experiments show that a 97% recognition rate can be achieved in an indoor environment, and a 90% recognition accuracy can be achieved in an outdoor environment in time.

关键词： Wireless sensor networks Time-frequency analysis Accuracy LoRa Fingerprint recognition Feature extraction security Time-domain analysis Signal to noise ratio Radiofrequency identification

来源：评论

学校读者我要写书评

暂无评论

Integrated high-performance error correction for continuous-variable quantum key distribution

arXiv

引用

arXiv 2024年

作者： Zhou, Chuang Li, Yang Ma, Li Yang, Jie Huang, Wei Sun, Ao Wang, Heng Luo, Yujie Li, Yong Chen, Ziyang Lau, Francis C.M. Zhang, Yichen Yu, Song Guo, Hong Xu, Bingjie National Key Laboratory of Security Communication Institute of Southwestern Communication Chengdu610041 China College of Computer Science Chongqing University Chongqing400044 China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Center for Quantum Information Technology Peking University Beijing100871 China Department of Electronic and Information Engineering Hong Kong Polytechnic University Hong Kong State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications Beijing100876 China

An integrated error-correction scheme with high throughput, low frame errors rate (FER) and high reconciliation efficiency under low signal to noise ratio (SNR) is one of the major bottlenecks to realize high-performance and low-cost continuous variable quantum key distribution (CV-QKD). To solve this long-standing problem, a novel two-stage error correction method with limited precision that is suitable for integration given limited on-chip hardware resource while maintaining excellent decoding performance is proposed, and experimentally verified on a commercial FPGA. Compared to state-of-art results, the error-correction throughput can be improved more than one order of magnitude given FER © 2024, CC BY.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

A biosensing system using a multiparameter nonlinear dynamic analysis of cardiomyocyte beating for drug-induced arrhythmia recognition

引用

Microsystems & Nanoengineering 2022年第3期8卷 277-290页

作者： Hao Wang Yue Wu Quchao Zou Wenjian Yang Zhongyuan Xu Hao Dong Zhjing Zhu Depeng Wang Tanxing Wang Ning Hu Diming Zhang State Key Laboratory of Optoelectronic Materials and Technologies Guangdong Province Key Laboratory of Display Material and TechnologySchool of Electronics and Information TechnologySun Yat-sen UniversityGuangzhou 510006China Research Center for Itelligent Sensing Systems Zhejiang LabHangzhou 311121China ZJU-Hangzhou Global Scientific and Technological Innovation Center Department of ChemistryThe Second Affiliated Hospital Zhejiang University School of MedicineDepartment of Clinical Medical EngineeringZhejiang UniversityHangzhou 310058China Key Laboratory of Novel Target and Drug Study for Neural Repair of Zhejang Province School of MedicineSchool of Computer&Computing ScienceZhejiang University City CollegeHangzhou 310015China School of Brain Science and Brain Medicine Zhejiang UniversityHangzhou 310058China College of Energy and Power Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China E-LinkCare Meditech Co LtdHangzhou 310011China State Key Laboratory of Transducer Technology Chinese Academy of SciencesShanghai 200050China

Cardiovascular disease is the number one cause of death in ***,cardiotoxicity is one of the most important adverse effects assessed by arrhythmia recognition in drug ***,cell-based techniques developed for arhythmia recognition primarily employ linear methods such as time-domain analysis that detect and compare individual waveforms and thus fall short in some applications that require automated and efficient arrhythmia recognition from large *** carried out the frst report to develop a biosensing system that integrated impedance measurement and multiparameter nonlinear dynamic algorithm(MNDA)analysis for druginduced arrhythmia recognition and *** biosensing system cultured cardiomyocytes as physiologically relevant models,used interdigitated electrodes to detect the mechanical beating of the cardiomyocytes,and employed MNDA analysis to recognize drug-induced arrhythmia from the cardiomyocyte beating *** best performing MNDA parameter,approximate entropy,enabled the system to recognize the appearance of sertindoleand norepinephrine-induced arrhythmia in the *** MNDA reconstruction in phase space enabled the system to classify the different arrhythmias and quantify the severity of *** new biosensing system utilizing MNDA provides a promising and alternative method for drug-induced arrhythmia recognition and classification in cardiological and pharmaceutical applications.

关键词： arrhythmia cardio analysis

来源：评论

学校读者我要写书评

暂无评论

SDNVD-SCADA: A formalized vulnerability detection platform in SDN-Enabled SCADA system 13th

SDNVD-SCADA: A formalized vulnerability detection platform i...

引用

13th Conference on Advanced computer Architecture, ACA 2020

作者： Zhao, Jinjing Pang, Ling Lin, Bai National Key Laboratory of Science and Technology on Information System Security Beijing China Beijing Institute of System Engineering Beijing China

ISBN: (纸本)9789811581342

After the Stunex event in 2010, the security problems of SCADA reveal to the public, which abstract more and more researchers to design new security firms to address the security problems of SCADA. Especially, after the software defined network (SDN) arose, it has become a beneficial attempt to improve the SCADA security. In this paper, a formalized vulnerability detection platform named SDNVD-SCADA is presented based on the SDN technology, which can be used to find the most familiar vulnerabilities in SCADA design, implementation, deployment and action processes. A general security mechanism description language and a SCADA vulnerability pattern database are embedded in SDNVD-SCADA to achieve the ambition of automatic vulnerability detection. © Springer Nature Singapore Pte Ltd 2020.

关键词： SCADA systems

来源：评论

学校读者我要写书评

暂无评论

StinAttack: A Lightweight and Effective Adversarial Attack Simulation to Ensemble IDSs for Satellite- Terrestrial Integrated Network

StinAttack: A Lightweight and Effective Adversarial Attack S...

引用

IEEE Symposium on computers and Communications (ISCC)

作者： Shangyuan Zhuang Jiyan Sun Hangsheng Zhang Xiaohui Kuang Ling Pang Haitao Liu Yinlong Liu School of Cyber Security University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China National Key Laboratory of Science and Technology on Information System Security Beijing China Computer Network Information Center Chinese Academy of Sciences Beijing China

ISBN: (数字)9781665497923

ISBN: (纸本)9781665497930

Effective adversarial attacks simulation is essential for the deployment of ensemble Intrusion Detection systems (en- semble IDSs) in Satellite-Terrestrial Integrated Network (STIN). This is because it can automatically generate a large amount of adversarial samples to evaluate the robustness of different classifiers. Based on the result, it can further guide the STIN engineers to select proper classifiers in ensemble IDSs. Moreover, it can help the IDSs improve detect performance by their self- learning property in the adversarial attack process. However, the existing adversarial attack approaches suffer from the problems of low success rate and high overhead of communication and calculation due to the limited computing resources and long communication links of STIN. This results in their inefficiency in STIN. To address the above problems, we provide StinAttack as a robustness evaluation scheme for STIN. First, StinAttack provides a comprehensive and automatic robustness evaluation framework for IDSs in STIN with only few times interactions between terrestrial and satellite nodes. Second, StinAttack proposes an effective adversarial attack simulation based on lightweight gradient evaluation for ensemble IDSs. Third, we conduct experiments on 11 typical IDSs, 4 baseline popular adversarial attacks and our StinAttack. Experimental results show that our approach can effectively attack ensemble IDSs and the evaluation results based on real STIN dataset are instructive for designing secure networks.

关键词： computers 6G mobile communication Satellites Computational modeling Intrusion detection Robustness security

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：