检索结果-内蒙古大学图书馆

7th IEEE International Conference on Data Science in Cyberspace, DSC 2022

作者： Liu, Zhehui Wang, Zhongru Zhang, Yuntao Liu, Tong Fang, Binxing Pang, Zhengyuan Ministry of Education Key Laboratory of Trustworthy Distributed Computing and Service Beijing China Chinese Academy of Cyberspace Studies Beijing China North China University of Technology School of Information Science and Technology Beijing100144 China Beijing DigApis Technology Co. Ltd Beijing100871 China JiangSu DigApis Technology Co. Ltd Jiangsu Nantong226000 China

ISBN: (数字)9781665474801

ISBN: (纸本)9781665474801

Recently, more and more software vulnerabilities are disclosed and researchers tend to study on automatically discover and exploit the vulnerabilities. However, the main challenges of automated exploit generation are: 1) it is hard to analyze the program failure and extract useful information, 2) the scenario of the vulnerability too complex to successfully exploit. Therefore, This paper proposes a vulnerability exploit generation framework AEG-E. AEG-E can extract the control flow graph from the target program and employ the crash reproduce algorithm in symbolic execution to reduce the problem of path explosion. To adapt to complex vulnerability scenarios, we design the extendable and user-configurable exploit model to generate different exploit. Finally, we used the binaries from Robo Hacking Games and real world program to demonstrate the validity and efficiency of AEG-E. The experiment results shows that AEG-E is 2.913 times more efficient than previous exploit generation tool, REX. © 2022 IEEE.

关键词： Flow graphs

来源：评论

学校读者我要写书评

暂无评论

A deepfake video detection method based on multi-modal deep learning method

A deepfake video detection method based on multi-modal deep ...

引用

International Conference on Electronics, Communications and Information Technology (CECIT)

作者： Yutong Zhang Xiaoyong Li Jie Yuan Yali Gao Linghui Li Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing P.R. China

ISBN: (纸本)9781665437585

Recently, most deepfake video classification tasks depend on frame-level features and try to train deep neural networks to characterize fake videos. Although this kind of methods can achieve good results, they also waste the audio information and timing information of the deepfake video dataset. Therefore, to make better use of the audio information, we propose a multi-modal method to detect deepfake videos. The principle of our method is based on the mismatch between audio information and visual information, such as the inconsistency of mouth shape and voice. We calculate the modality dissonance score(MDS score) of videos to classify true/false videos. Extensive experiments reach 84.4% accuracy on the DFDC dataset, which demonstrates the effectiveness of our method.

关键词： Deep learning Visualization Shape Neural networks Mouth Timing Information and communication technology

来源：评论

学校读者我要写书评

暂无评论

CWAI-CNER: Chinese entity recognition based on adaptive incorporation of characters and words

CWAI-CNER: Chinese entity recognition based on adaptive inco...

引用

Consumer Electronics and Computer Engineering (ICCECE), 2021 IEEE International Conference on

作者： Pai Peng Xu Wu Xiaqing Xie Jingchen Wu Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Cyberspace Security BUPT Beijing China Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Cyberspace Security Beijing University of Posts and Telecommunications Library BUPT Beijing China

ISBN: (数字)9781728183190

ISBN: (纸本)9781728183206

Chinese Named Entity Recognition (CNER) is an important sub topic in the field of Chinese Natural Language Processing, which plays an important role in multi tasks. However, it's difficult to determine the boundaries of entities in Chinese texts because the Chinese words are not naturally separated, which further causes the task of CNER much more difficult. In addition, the mainstream Named Entity Recognition (NER) is based on sequence tagging, which causes the cost of training set labeling very high, so many NER tasks are limited by training sets' deficiency. In this work, we propose a new CNER method based on adaptive incorporation of characters and words-CWAI to solve the problem of words information loss caused by lacking of words boundaries, which uses convolution neural network (CNN) to capture the local semantics for every character, and then adaptively calculates the weights of potential words that match a lexicon for each character based on attention mechanism between characters and words. And for the problem of limited model effects due to insufficient training set, we combined our model with pre-trained models to solve that.

关键词： Training Adaptation models Semantics Tagging Character recognition Task analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

Training for stable explanation for free 24

Training for stable explanation for free

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Chao Chen Chenghua Guo Rufeng Chen Guixiang Ma Ming Zeng Xiangwen Liao Xi Zhang Sihong Xie School of Computer Science and Technology Harbin Institute of Technology (Shenzhen) China Key Laboratory of Trustworthy Distributed Computing and Service (MoE) Beijing University of Posts and Telecommunications China Artificial Intelligence Thrust The Hong Kong University of Science and Technology (Guangzhou) China Intel Carnegie Mellon University College of Computer and Data Science Fuzhou University China

ISBN: (纸本)9798331314385

To foster trust in machine learning models, explanations must be faithful and stable for consistent insights. Existing relevant works rely on the ℓp distance for stability assessment, which diverges from human perception. Besides, existing adversarial training (AT) associated with intensive computations may lead to an arms race. To address these challenges, we introduce a novel metric to assess the stability of top-k salient features. We introduce R2ET which trains for stable explanation by efficient and effective regularizer, and analyze R2ET by multi-objective optimization to prove numerical and statistical stability of explanations. Moreover, theoretical connections between R2ET and certified robustness justify R2ET's stability in all attacks. Extensive experiments across various data modalities and model architectures show that R2ET achieves superior stability against stealthy attacks, and generalizes effectively across different explanation methods. The code can be found at https://***/ccha005/R2ET.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EFM: A Negative Network Public Opinion Early Warning Model Based on Evolutionary Feature Mining

EFM: A Negative Network Public Opinion Early Warning Model B...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Fanfeixue Meng Jingchen Wu Feifan Song Xu Wu Lan Hu Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Cyberspace Security BUPT Beijing University of Posts and Telecommunications Beijing China School of Computer Science (National Pilot Software Engineering School) BUPT School of Economics and Finance Changchun Finance College

With the popularity of the Internet and the increase in the number of netizens, it is of great significance to effectively monitor and predict the negative network public opinion on social media platforms. Most mainstream negative network public opinion early warning models mainly focus on mining textual features, while neglecting the response and dissemination among netizens during the process of negative network public opinion fermentation. This is one of the important reasons for the accuracy bottleneck of them. This article proposes a negative network public opinion early warning model based on evolutionary feature mining. Firstly, by using entity linking techniques based on knowledge graphs, domain prior knowledge is supplemented for the text need to be analyzed for negative network public opinion. Then, the text sentiment features extracted based on long short-term memory networks and the evolutionary features extracted based on graph convolutional networks are fused through an enhanced-feature fusion method. Finally, the features are used for classification and early warning. Experimental results based on the Weibo public dataset show that the EFM model has higher early warning performance for negative network public opinion compared to other baseline models. The accuracy of this model is 0.959.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A hierarchical sharing mechanism based privacy data protection

A hierarchical sharing mechanism based privacy data protecti...

引用

Science and Technology Innovation (IAECST), International Academic Exchange Conference on

作者： Zhaxi Namjie Tianbo Lu Yanjiao Gong Jiaze Shang Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665402682

The frequent occurrence of privacy data breaches and the subsequent issuance of data security laws and regulations have led to increased attention paid to the security of personal data. Ensuring the safety of personal privacy data while releasing data has become a significant challenge. Most of the existing privacy protection models provide the same query results for all data queries without considering the demand for data accuracy by different users, the privacy differences of data with different attributes, and the risk of privacy leakage caused by multiple queries. Based on this, this paper proposes a centralized differential privacy-based data hierarchical query algorithm from the data querier's demand for data precision in the data publishing scenario. Firstly, the corresponding trust level is calculated based on the three attribute values of the trust value of the data querier, the query authority level and the privacy level of the query data, and the privacy protection parameters corresponding to the trust level are used to realize the grading of the data querier. Secondly, the privacy budget parameters are set to avoid the risk of privacy leakage caused by multiple queries made by attackers. At the same time, the McSherry-Laplace mean algorithm is improved to reduce the error rate while ensuring that it satisfies differential privacy. The experimental results show that the above algorithm processes different datasets to provide accurate and differentiated usable data for various data querier users while satisfying differential privacy.

关键词： Data privacy Differential privacy Privacy Technological innovation Error analysis Publishing Perturbation methods

来源：评论

学校读者我要写书评

暂无评论

EML-Based IM/DD Transmission over Dispersion-Uncompensated Links Using Low-Complexity Optimized Detection

EML-Based IM/DD Transmission over Dispersion-Uncompensated L...

引用

2021 Asia Communications and Photonics Conference, ACP 2021

作者： Liu, Shuangyue Cui, Han Tang, Xizi Lu, Yueming Qiao, Yaojun State Key Laboratory of Information Photonics and Optical Communications School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing100876 China

We experimentally demonstrate an EML-based 40-Gbit/s OOK IM/DD transmission over 120-km SSMF using a low-complexity optimized detection algorithm, which requires no multiplication during the update of survival path, s... 详细信息

ISBN: (纸本)9781957171005

关键词： Chromatic dispersion

来源：评论

学校读者我要写书评

暂无评论

A survey of automated International Classification of Diseases coding:development,challenges,and applications

引用

Intelligent Medicine 2022年第3期2卷 161-173页

作者： Chenwei Yan Xiangling Fu Xien Liu Yuanqiu Zhang Yue Gao Ji Wu Qiang Li School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876China Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Ministry of EducationBeijing 100876China Department of Electronic Engineering Tsinghua UniversityBeijing 100084China Beijing Tsinghua Changgung Hospital Beijing 102218China

The International Classification of Diseases(ICD)is an international standard and tool for epidemiological in-vestigation,health management,and clinical diagnosis with a fundamental role in intelligent medical *** assignment of ICD codes to health-related documents has become a focus of academic research,and numerous studies have developed the process of ICD coding from manual to automated *** this survey,we review the developmental history of this task in recent decades in depth,from the rules-based stage,through the traditional machine learning stage,to the neural-network-based *** methods have been introduced to solve this problem by using different techniques,and we report a performance comparison of different methods on the pub-licly available Medical Information Mart for Intensive Care ***,we summarize four major challenges of this task:(1)the large label space,(2)the unbalanced label distribution,(3)the long text of documents,and(4)the interpretability of *** solutions that have been proposed to solve these problems are ***,we discuss the applications of ICD coding,from mortality statistics to payments based on disease-related groups and hospital performance *** addition,we discuss different ways of considering and evaluat-ing this task,and how it has been transformed into a learnable *** also provide details of the commonly used ***,this survey aims to provide a reference and possible prospective directions for follow-up research work.

关键词： International Classification of Diseases coding Disease classification Health-related document Electronic medical record Medical record management Clinical coding

来源：评论

学校读者我要写书评

暂无评论

Decode the Dark Side of the Language: Applications of LLMs in the Dark Web

Decode the Dark Side of the Language: Applications of LLMs i...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Hongfan Chen Yigang Diao Hui Xiang Yixuan Huo Xiaqing Xie Jiapeng Zhao Xuebin Wang Yanwei Sun Jinqiao Shi School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing China Cyberspace Administration of China Data and Technology Support Center Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Previous studies have discovered that Transformers pre-trained on large scale datasets have a great advantage over traditional methods and can achieve human-level performance in many NLP tasks. Various encoder-only models like BERT and RoBERTa are used in the researches of the language in the Dark Web and most of them have achieved state-of-the-art performance. However, decoder-only models are not frequently used as they were considered to be unsuitable for NLU tasks until recent advancements in large language models. In this paper, we discuss the application of large scale decoder-only models in NLP tasks of real-world Dark Web research. We explore the capabilities of these models with the most realistic datasets in this specific domain. Surprisingly, results show that decoder-only models can achieve similar or better performance compared with state-of-the-art encoder-only model in some cases and show their own unique advantages in such field. We also discuss the limitations of these models and the challenges associated with their application in such field. Our study unveils the potential of decoder-only models in NLP tasks of real-world Dark Web research.

关键词： Dark Web Large language models Text categorization Zero shot learning Cyberspace Data science Transformers Natural language processing Data models Encoding

来源：评论

学校读者我要写书评

暂无评论

DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation

arXiv

引用

arXiv 2022年

作者： Huang, Mengqi Mao, Zhendong Wang, Penghui Wang, Quan Zhang, Yongdong University of Science and Technology of China China MOE Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China

Text-to-image generation aims at generating realistic images which are semantically consistent with the given text. Previous works mainly adopt the multi-stage architecture by stacking generator-discriminator pairs to engage multiple adversarial training, where the text semantics used to provide generation guidance remain static across all stages. This work argues that text features at each stage should be adaptively re-composed conditioned on the status of the historical stage (i.e., historical stage's text and image features) to provide diversified and accurate semantic guidance during the coarse-to-fine generation process. We thereby propose a novel Dynamical Semantic Evolution GAN (DSE-GAN) to re-compose each stage's text features under a novel single adversarial multi-stage architecture. Specifically, we design (1) Dynamic Semantic Evolution (DSE) module, which first aggregates historical image features to summarize the generative feedback, and then dynamically selects words required to be re-composed at each stage as well as re-composed them by dynamically enhancing or suppressing different granularity subspace's semantics. (2) Single Adversarial Multistage Architecture (SAMA), which extends the previous structure by eliminating complicated multiple adversarial training requirements and therefore allows more stages of text-image interactions, and finally facilitates the DSE module. We conduct comprehensive experiments and show that DSE-GAN achieves 7.48% and 37.8% relative FID improvement on two widely used benchmarks, i.e., CUB-200 and MSCOCO, respectively. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

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：