检索结果-内蒙古大学图书馆

IEEE Symposium on security and Privacy

作者： Jiawei Yin Menghao Li Yuekang Li Yong Yu Boru Lin Yanyan Zou Yang Liu Wei Huo Jingling Xue Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing Key Laboratory of Network Assessment Technology Chinese Academy of Sciences Beijing Key Laboratory of Network Security and Protection Technology Nanyang Technological University UNSW Sydney

System Management Mode (SMM) is a secure operation mode for x86 processors supported by Unified Extensible Firmware Interface (UEFI) firmware. SMM is designed to provide a secure execution environment to access highly privileged data or control low-level hardware (such as power management). The programs running in SMM are called SMM drivers and System Management Interrupt (SMI) handlers are the most important components of SMM drivers since they are the only components to receive and handle data from outside the SMM execution environment. Although SMM can serve as an extra layer of protection when the operating system is compromised, vulnerabilities in SMM drivers, especially SMI handlers, can invalidate this protection and cause severe damages to the device. Thus, early detection of SMI handler vulnerabilities is important for UEFI firmware *** this end, researchers have proposed to use hybrid fuzzing techniques for detecting SMI handler vulnerabilities. Particularly, Intel has developed a hybrid fuzzer called Excite and uses it to secure Intel products. Although existing hybrid fuzzing techniques can detect vulnerabilities in SMI handlers, their effectiveness is limited due to two major pitfalls: 1) They can only feed input through the most common input interface to SMI handlers, lacking the ability to utilize other input interfaces. 2) They have no awareness of variables shared by multiple SMI handlers, lacking the ability to explore code segments related to such variables. By addressing the challenges faced by existing works, we propose RSFuzzer, a hybrid greybox fuzzing technique which can learn input interface and format information and detect deeply hidden vulnerabilities which are triggered by invoking multiple SMI handlers. We implemented RSFuzzer and evaluated it on 16 UEFI firmware images provided by six vendors. The experiment results show that RSFuzzer can cover 617% more basic blocks and detect 828% more vulnerabilities on average than the stat

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey of Deep Visual Cross-Domain Few-Shot Learning

arXiv

引用

arXiv 2023年

作者： Wang, Wenjian Duan, Lijuan Wang, Yuxi Fan, Junsong Gong, Zhi Zhang, Zhaoxiang Faculty of Information Technology Beijing University of Technology China Beijing Key Laboratory of Trusted Computing Beijing China National Engineering Laboratory for Key Technologies of Information Security Level Protection Beijing China Centre for Artificial Intelligence and Robotics HKISI_CAS Institute of Automation Chinese Academy of Sciences [NLPR CASIA UCAS China

Few-Shot transfer learning has become a major focus of research as it allows recognition of new classes with limited labeled data. While it is assumed that train and test data have the same data distribution, this is often not the case in real-world applications. This leads to decreased model transfer effects when the new class distribution differs significantly from the learned classes. Research into Cross-Domain Few-Shot (CDFS) has emerged to address this issue, forming a more challenging and realistic setting. In this survey, we provide a detailed taxonomy of CDFS from the problem setting and corresponding solutions view. We summarise the existing CDFS network architectures and discuss the solution ideas for each direction the taxonomy indicates. Furthermore, we introduce various CDFS downstream applications and outline classification, detection, and segmentation benchmarks and corresponding standards for evaluation. We also discuss the challenges of CDFS research and explore potential directions for future investigation. Through this review, we aim to provide comprehensive guidance on CDFS research, enabling researchers to gain insight into the state-of-the-art while allowing them to build upon existing solutions to develop their own CDFS models. Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Automatic recognition of depression based on audio and video:A review

引用

World Journal of Psychiatry 2024年第2期14卷 225-233页

作者： Meng-Meng Han Xing-Yun Li Xin-Yu Yi Yun-Shao Zheng Wei-Li Xia Ya-Fei Liu Qing-Xiang Wang Shandong Mental Health Center Shandong UniversityJinan 250014Shandong ProvinceChina Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353Shandong ProvinceChina Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and TechnologyQilu University of Technology(Shandong Academy of Sciences)Jinan 250353Shandong ProvinceChina Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250353Shandong ProvinceChina Department of Ward Two Shandong Mental Health CenterShandong UniversityJinan 250014Shandong ProvinceChina

Depression is a common mental health *** current depression detection methods,specialized physicians often engage in conversations and physiological examinations based on standardized scales as auxiliary measures for depression ***-biological markers-typically classified as verbal or non-verbal and deemed crucial evaluation criteria for depression-have not been effectively *** physicians usually require extensive training and experience to capture changes in these *** in deep learning technology have provided technical support for capturing non-biological *** researchers have proposed automatic depression estimation(ADE)systems based on sounds and videos to assist physicians in capturing these features and conducting depression *** article summarizes commonly used public datasets and recent research on audio-and video-based ADE based on three perspectives:Datasets,deficiencies in existing research,and future development directions.

关键词： Depression recognition Deep learning Automatic depression estimation System Audio processing Image processing Feature fusion Future development

来源：评论

学校读者我要写书评

暂无评论

A Digital Interface-Based Digital Rights Management Scheme for Digital Cinema

引用

Chinese Journal of Electronics 2023年第3期19卷 481-485页

作者： Kefeng Fan Zhaofeng Ma Yixian Yang Xinxin Niu State Key Laboratory of Networking and Switching Technology Information Security Center Beijing University of Posts and Telecommunications Beijing China National Engineering Laboratory for Disaster Backup and Recovery Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Network and Information Attack and Defence Technology of MOE Beijing University of Posts and Telecommunications Beijing China

Digital rights management (DRM) is indispensable to prevent various kinds of illegal content usage. In this paper, we present a Digital interface-based DRM scheme (DI-DRM) for digital cinema, which can provide a new multi-interfaces oriented DRM solution for digital cinema. The authentication protocol and the encryption algorithm are described in detail. The two kinds of digital interfaces-based DRM prototype system are developed. security and performance analysis show the proposed scheme has several advantages. First, it is more secure than the existing scheme. Second, it is supported more rights, including the downstream devices. Finally, the cost of the chip based on DI-DRM is low. The scale of SOC application scheme is only 1/3 to 1/6 of the existing DTCP.

关键词： Protocols Prototypes Authentication Medical services Copyright protection Motion pictures Performance analysis

来源：评论

学校读者我要写书评

暂无评论

A Survey of Deep Models for Cross-Domain Few-Shot Visuallearning

SSRN

引用

SSRN 2023年

作者： Wang, Wenjian Duan, Lijuan Wang, Yuxi Fan, Junsong Gong, Zhi Zhang, Zhaoxiang Faculty of Information Technology Beijing University of Technology China Beijing Key Laboratory of Trusted Computing Beijing China National Engineering Laboratory for Key Technologies of Information Security Level Protection Beijing China Centre for Artificial Intelligence and Robotics HKISI CAS Hong Kong Institute of Automation Chinese Academy of Sciences NLPR CASIA UCAS China

Few-Shot transfer learning uses limited labeled data to recognise the new classes. Current researches assume that train and test data have the same data distribution. But this setting is strict and difficult to guarantee due to the various transfer scenarios in reality. When the new class distribution different from the learned classes significantly, the model transfer effect will be seriously decreased. To relieve this problem, the existing Few-Shot research has begun to focus on cross-domain research, hoping the model can still complete Few-Shot learning when facing the domain shift, namely Cross-Domain Few-Shot (CDFS). Compared with standard Few-Shot learning, CDFS is more challenging and suitable to actual scenarios. We summarized recent research on Cross-Domain Few-Shot. Our survey provide the detailed taxonomy from the view of problem setting and corresponding solutions. We introduced the typical CDFS network in detail in each taxonomy direction and summarized the solution ideas. Meanwhile, we introduce the various CDFS downstream application. Furthermore, we outlined the classification, detection, and segmentation of the corresponding CDFS benchmark and give the corresponding standards for subsequent research. Finally, we summarized the challenges of CDFS in the future and the related technical direction, hoping to provide corresponding guidance for future CDFS research. © 2023, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Classification of epilepsy period based on combination feature extraction methods and spiking swarm intelligent optimization algorithm

Classification of epilepsy period based on combination featu...

引用

作者： Duan, Lijuan Lian, Zhaoyang Chen, Juncheng Qiao, Yuanhua Miao, Jun Li, Mingai Faculty of Information Technology Beijing University of Technology Beijing China Beijing Key Laboratory of Trusted Computing Beijing University of Technology Beijing China National Engineering Laboratory for Key Technologies of Information Security Level Protection Beijing University of Technology Beijing China Applied Sciences Beijing University of Technology Beijing China School of Computer Science Beijing Information Science and Technology University Beijing China

Epilepsy seriously damages the physical and mental health of patients. Detection of epileptic EEG signals in different periods can help doctors diagnose the disease. The change of frequency components during epilepsy seizures is obvious, and there may be noises in epilepsy EEG signals. Moreover, epileptic seizures are closely related to the release of neuronal spiking in the brain. In this paper, we propose an approach for epilepsy period classification based on combination feature extraction methods and spiking swarm intelligent optimization classification algorithm. First, combination feature extraction methods take in account both the time-frequency features and principal component features of epilepsy. The time-frequency features are obtained by WPT or STFT-PSD, and noises are removed while extracting principal component features by PCA. Second, spiking swarm intelligent optimization classification algorithm takes advantage of individual cooperation and information interaction with strong robustness. Its simulated neurons are closer to reality, which consider more information and obtain stronger computing power. The experimental results show that the average classification accuracy of the proposed method can reach 98.95% and the highest classification accuracy can reach 100%. Compared with other methods, the proposed method has the best classification performance. © 2020 John Wiley & Sons, Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

BPN: Bidirectional Path Network for Instance Segmentation 1st

BPN: Bidirectional Path Network for Instance Segmentation

引用

1st CAAI International Conference on Artificial Intelligence, CICAI 2021

作者： Xu, Fan Duan, Lijuan Qiao, Yuanhua Faculty of Information Technology Beijing University of Technology Beijing China Peng Cheng Laboratory Beijing University of Technology Beijing China Beijing Key Laboratory of Trusted Computing Beijing University of Technology Beijing China National Engineering Laboratory for Key Technologies of Information Security Level Protection Beijing University of Technology Beijing China College of Mathematics and Physics Beijing University of Technology Beijing China

ISBN: (纸本)9783030930486

The feature pyramid network (FPN) has achieved impressive results in the field of object detection and instance segmentation by aggregating features of different scales, especially the detection of small objects. However, for some special large objects (such as tables, chairs, etc.), It is difficult to achieve good results for FPN. In this paper, we propose a new simple but effective network, the Bidirectional Path Network (BPN), for the problems that FPN cannot solve. In simple terms, it consists of a top-to-down FPN and bottom-to-up FPN. This bidirectional network structure can greatly enrich high-level semantic information and improve the detection effect of these large objects. And we also introduce dense connections to enrich the output features further. We tested our method on the COCO dataset. Firstly, on the object detection task, our method obtains comparable results with the state-of-the-art benchmark. Then, on the instance segmentation task, our method also achieved good results. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Federated Learning with Homomorphic Encryption and Sparse Compression

Privacy-Preserving Federated Learning with Homomorphic Encry...

引用

Computer Communication and Artificial Intelligence (CCAI), International Conference on

作者： Wentao Yang Yang Bai Yutang Rao Hongyan Wu Gaojie Xing Yimin Zhou School of Cybersecurity (Xin Gu Industrial College) Chengdu University of Information Technology Chengdu China National Engineering Research Center for Advanced Microprocessor Technology Industrial Control and Security Chengdu China Energy Equipment Cyber Security Key Laboratory of Sichuan Province Chengdu China

ISBN: (数字)9798350362763

ISBN: (纸本)9798350362770

Federated learning attempts to train a machine learning algorithm on several local datasets stored on local nodes without needing direct data sample exchange to avoid data leaking. However, recent research has shown that Federal Learning still faces many privacy threats, such as membership inference attacks, model inversion attacks, etc. Differential privacy and homomorphic encryption are two main categories of privacy protection methods used to defend against these threats. Although differential privacy is effective against privacy risks, it can also lead to lower model accuracy. Although homomorphic encryption is effective against privacy threats while having less impact on model accuracy, it imposes extensive communication and computational costs. In this paper, we propose an approach that utilises sparsification techniques and compressive sensing to reduce the computational and communication overhead of homomorphic cryptographic federation learning. Then, we conduct experiments based on Paillier homomorphic encryption federated learning under MNIST and Fashion-MNIST datasets, and the experimental results show that our method can reduce the encryption time from 7.75 seconds to 0.70 seconds, with a 90 % reduction in computational overhead and it can also reduce the decryption time from 5.23 seconds to 0.66 seconds, with a decrease in computational overhead of 88%. The communication overhead is reduced from 2494.56KB to 163.78KB, which is 93.4%. Meanwhile, the model accuracy under the MNIST dataset decreased from 98.47% to 98.37%; the model accuracy under the Fashion-MNIST dataset increased from 89.64% to 90.16%.

关键词： Privacy Differential privacy Accuracy Federated learning Computational modeling Sparse matrices Servers

来源：评论

学校读者我要写书评

暂无评论

An efficient method for analyzing widget intent of android system 2021

An efficient method for analyzing widget intent of android s...

引用

9th International Conference on Communications and Broadband Networking, ICCBN 2021

作者： Qi, Chunhao Shao, Shuai Guo, Yanhui Peng, Junhao Xu, Guosheng Beijing University of Posts and Telecommunications National Engineering Laboratory of Mobile Network Security Beijing China China Information Technology Security Evaluation Center Beijing China School of Math and Information Science Guangdong Prov. Key Laboratory Co-sponsored by Province and City of Information Security Technology Guangzhou University Guangzhou China

ISBN: (纸本)9781450389174

With the improvement of the status of mobile phones and other mobile terminals in life, the privacy protection of mobile phones is still a big problem. Aiming at the Android system, the mobile terminal operating system with the largest share today, this paper proposes a widget intention analysis method to solve the problem of how to judge the user's operation intention in privacy protection. This intention analysis method uses MobilenetV3 to extract image information, BiLSTM to extract text information, then constructs joint features together, and uses deep learning technology to realize intention analysis of widgets. Through comparative experiments, our method improves the detection accuracy and reduces the training time for the existing methods. © 2021 ACM.

关键词： Cellular telephones

来源：评论

学校读者我要写书评

暂无评论

Concept and Research Framework for Coordinated Situation Awareness and Active Defense of Cyber-physical Power Systems Against Cyber-attacks

引用

Journal of Modern Power Systems and Clean Energy 2021年第3期9卷 477-484页

作者： Ming Ni Manli Li Jun’e Li Yingjun Wu Qi Wang the NARI Group Corporation(State Grid Electric Power Research Institute) NARI Technology Co.Ltd.and the State Key Laboratory of Smart Grid Protection and ControlNanjing 211106China the School of Cyber Science and Engineering Wuhan Universityand the Key Laboratory of Aerospace Information Security and Trusted Computing of the Ministry of EducationWuhan 430072China the College of Energy and Electrical Engineering Hohai UniversityNanjing 211100China the School of Electrical Engineering Southeast UniversityNanjing 210096China

Due to the tight coupling between the cyber and physical sides of a cyber-physical power system(CPPS),the safe and reliable operation of CPPSs is being increasingly impacted by cyber *** situation poses a challenge to traditional security defense systems,which considers the threat from only one side,i.e.,cyber or *** cope with cyberattacks,this paper reaches beyond the traditional one-side security defense systems and proposes the concept of cyber-physical coordinated situation awareness and active defense to improve the ability of *** example of a regional frequency control system is used to show the validness and potential of this ***,the research framework is presented for studying and implementing this ***,key technologies for cyber-physical coordinated situation awareness and active defense against cyber-attacks are introduced.

关键词： Cyber-physical power system(CPPS) cyber security cyber-attack situation awareness active defense

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：