2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)最新文献_第3页

An Anomaly Detection Method for System Logs Using Venn-Abers Predictors 基于Venn-Abers预测因子的系统日志异常检测方法

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00063

Lanlan Pan, Zhaojun Gu, Yitong Ren, Chunbo Liu, Zhi Wang

{"title":"An Anomaly Detection Method for System Logs Using Venn-Abers Predictors","authors":"Lanlan Pan, Zhaojun Gu, Yitong Ren, Chunbo Liu, Zhi Wang","doi":"10.1109/DSC50466.2020.00063","DOIUrl":"https://doi.org/10.1109/DSC50466.2020.00063","url":null,"abstract":"System logs can record the system status and important events during system operation in detail. Detecting anomalies through the system log is a common method for modern large-scale distributed systems. While using machine learning algorithms to system log anomaly detection, the output of threshold-based classification models are only normally or abnormally simple predictions, which lacks probability of estimating whether the prediction results are correct. In this paper, a statistical learning algorithm Venn-Abers predictor is used to evaluate the confidence of prediction results in the field of system log anomaly detection. It is able to calculate the label probability distribution for a set of samples, and provides a quality assessment of predictive labels with a degree of certainty. Two Venn-Abers predictors were implemented based on logistic regression and support vector machine. Then, experiments are carried out on the log data set of the distributed me management system HDFS. Besides, two Venn-Abers predictors and two underlying algorithms are compared in terms of log anomaly detection accuracy and validity. Compared with underlying machine learning algorithms, the Venn-Abers predictor based on support vector machine can achieve better results. It reduces the false positive rate from 12% to 3%, and improve the recall rate from 81% to 94%, besides, the loss value can be reduced to 0.04. Experimental results show that Venn-Abers is a flexible tool that can make accurate and valid probability predictions in the field of system log anomaly detection.","PeriodicalId":423182,"journal":{"name":"2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134479366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

On Improving the Learning of Long-Term historical Information for Tasks with Partial Observability 提高部分可观察任务长期历史信息的学习

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00042

Xinwen Wang, Xin Li, Linjing Lai

{"title":"On Improving the Learning of Long-Term historical Information for Tasks with Partial Observability","authors":"Xinwen Wang, Xin Li, Linjing Lai","doi":"10.1109/DSC50466.2020.00042","DOIUrl":"https://doi.org/10.1109/DSC50466.2020.00042","url":null,"abstract":"Reinforcement learning (RL) has been recognized as the powerful tool to handle many real-work tasks of decision making, data mining and, information retrieval. Many well-developed RL algorithms have been developed, however tasks involved with partially observable environment, e.g, POMDPs (Partially Observable Markov Decision Processes) are still very challenging. Recent attempts to address this issue is to memorize the long-term historical information by using deep neural networks. And the common strategy is to leverage the recurrent networks, e.g., Long Short-Term Memory(LSTM), to retain/encode the historical information to estimate the true state of environments, given the partial observability. However, when confronted with rather long history dependent problems and irregular data sampling, the conventional LSTM is ill-suited for the problem and difficult to be trained due to the well-known gradient vanishing and the inadequacy of capturing long-term history. In this paper, we propose to utilize Phased LSTM to solve the POMDP tasks, which introduces an additional time gate to periodically update the memory cell, helping the neural framework to 1) maintain the information of the long-term, 2) and propagate the gradient better to facilitate the training of reinforcement learning model with recurrent structure. To further adapt to reinforcement learning and boost the performance, we also propose a Self-Phased LSTM with incorporating a periodic gate, which is able to generate a dynamic periodic gate to adjust automatically for more tasks, especially the notorious ones with sparse rewards. Our experimental results verify the effectiveness of leveraging on such Phased LSTM and Self-Phased LSTM for POMDP tasks.","PeriodicalId":423182,"journal":{"name":"2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)","volume":"42 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133056274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Review of APT Attack Detection Methods and Defense Strategies APT攻击检测方法及防御策略综述

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00018

Kai Xing, Aiping Li, Rong Jiang, Yan Jia

引用次数: 6

A Study of Bitcoin De-Anonymization: Graph and Multidimensional Data Analysis 比特币去匿名化研究:图与多维数据分析

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00059

Xingyu Lv, Ye Zhong, Qingfeng Tan

{"title":"A Study of Bitcoin De-Anonymization: Graph and Multidimensional Data Analysis","authors":"Xingyu Lv, Ye Zhong, Qingfeng Tan","doi":"10.1109/DSC50466.2020.00059","DOIUrl":"https://doi.org/10.1109/DSC50466.2020.00059","url":null,"abstract":"Bitcoin was designed to be a decentralized global electronic payment system that does not require verification by a third-party intermediary platform and can be used by anyone originally. Due to its anonymity and globalization, bitcoin has achieved great success and attracted the attention of various illegal traders. In recent years, the number of illegal transactions of bitcoin has been increasing. Although bitcoin can support a certain amount of privacy, the bitcoin users and entity information can be linked by tracking the on-chain information of bitcoin users and combining the public off-chain information. Through bitcoin users de-anonymization, we can obtain some valuable intelligence information, which plays an important role in combating bitcoin-related crimes. In this paper, we build a visual analysis system for bitcoin transactions based on a graph database and use real-world multi-dimensional data sources to analyze the entity information of bitcoin transactions on the chain to achieve the effect of de-anonymization. Besides, we adopt a supervised learning method in our system to predict the legitimacy of unknown bitcoin transactions. Experiments and analyses show that our system can achieve good correlation analysis and de-anonymization. Finally, we put forward the future research direction of the bitcoin de-anonymization field.","PeriodicalId":423182,"journal":{"name":"2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133523369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Secure Data Dissemination among Multiple Base Stations in High-Speed Railway Network 高速铁路网中多基站数据传输的安全

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00025

Zhongbai Jiang, Yanwei Sun, Lei Shi, Weihua Hu, Zhaohui Liu

{"title":"Secure Data Dissemination among Multiple Base Stations in High-Speed Railway Network","authors":"Zhongbai Jiang, Yanwei Sun, Lei Shi, Weihua Hu, Zhaohui Liu","doi":"10.1109/DSC50466.2020.00025","DOIUrl":"https://doi.org/10.1109/DSC50466.2020.00025","url":null,"abstract":"In recent years, the number of users in High-Speed Rail (HSR) networks has been increasing dramatically, which further leads to the dramatic increment of service data carried by HSR networks. However, the extremely high mobility of high-speed train has brought great challenges to transmit service data with high quality and security. At first, the current researches on data transmission of HSR networks mainly uses the single base station model. That is, each of the mobile users is only able to communicate one base station. Although this analysis method is relatively viable and simple, it ignores the situation where multiple base stations can establish wireless communication links with users. Moreover, eavesdropping is also an important secure problem in wireless communication. However, the secrecy transmission technology has not been explicit researched in HSR networks to improve the security of network transmission. In response to these problems, this paper first abstracts a network model where multiple base stations can be used for wireless data transmission. The secrecy transmission, transmission power and data loss probability are also incorporated into the established model. Then an optimization problem is formulated. By solving the formulated problem, the Secure Data Distribution (SDD) mechanism is proposed. The performance of the SDD mechanism is evaluated by simulation experiments.","PeriodicalId":423182,"journal":{"name":"2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127263654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

DQ-MOTAG: Deep Reinforcement Learning-based Moving Target Defense Against DDoS Attacks 基于深度强化学习的移动目标DDoS攻击防御

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00065

Xinzhong Chai, Yasen Wang, Chuanxu Yan, Yuan Zhao, Wenlong Chen, Xiaolei Wang

{"title":"DQ-MOTAG: Deep Reinforcement Learning-based Moving Target Defense Against DDoS Attacks","authors":"Xinzhong Chai, Yasen Wang, Chuanxu Yan, Yuan Zhao, Wenlong Chen, Xiaolei Wang","doi":"10.1109/DSC50466.2020.00065","DOIUrl":"https://doi.org/10.1109/DSC50466.2020.00065","url":null,"abstract":"The rapid developments of mobile communication and wearable devices greatly improve our daily life, while the massive entities and emerging services also make Cyber-Physical System (CPS) much more complicated. The maintenance of CPS security tends to be more and more difficult. As a ”gamechanging” new active defense concept, Moving Target Defense (MTD) handle this tricky problem by periodically upsetting and recombining connections between users and servers in the protected system, which is so-called ”shuffle”. By this means, adversaries can hardly obtain enough time to compromise the potential victims, which is the indispensable condition to collect necessary information or conduct further malicious attacks. But every coin has two sides, MTD also introduce unbearable high energy consumption and resource occupation in the meantime, which hinders the large-scale application of MTD for quite a long time. In this paper, we propose a novel deep reinforcement learning-based MOTAG system called DQ-MOTAG. To our knowledge, this is the first work to provide self-adaptive shuffle period adjustment ability for MTD with reinforcement learning-based intelligent control mechanism. We also design an algorithm to generate optimal duration of next period to guide subsequent shuffle. Finally, we conduct a series of experiments to prove the availability and performance of DQ-MOTAG compared to exist methods. The result highlights our solution in terms of defense performance, error block rate and network source consumption.","PeriodicalId":423182,"journal":{"name":"2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122654220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

Knowledge Fusion and Spatiotemporal Data Cleaning: A Review 知识融合与时空数据清洗研究进展

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00052

Huchen Zhou, Mohan Li, Zhaoquan Gu

引用次数: 3

Sampling Topic Representative Users by Integrating Node Degree and Edge Weight 结合节点度和边权对具有代表性的用户进行抽样

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00062

Jiangwen Wang, Zhijie Ban

引用次数: 2

An Advanced BERT-Based Decomposition Method for Joint Extraction of Entities and Relations 一种基于bert的实体与关系联合抽取的高级分解方法

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00021

Changhai Wang, Aiping Li, Hongkui Tu, Ye Wang, Chenchen Li, Xiaojuan Zhao

{"title":"An Advanced BERT-Based Decomposition Method for Joint Extraction of Entities and Relations","authors":"Changhai Wang, Aiping Li, Hongkui Tu, Ye Wang, Chenchen Li, Xiaojuan Zhao","doi":"10.1109/DSC50466.2020.00021","DOIUrl":"https://doi.org/10.1109/DSC50466.2020.00021","url":null,"abstract":"Joint extraction of entities and relations is an important task in the field of natural language processing and the basis of many NLP high-level tasks. However, most existing joint models cannot solve the problem of overlapping triples well. We propose an efficient end-to-end model for joint extraction of entities and overlapping relations. Firstly, the BERT pre-training model is introduced to model the text more finely. Next, We decompose triples extraction into two subtasks: head entity extraction and tail entity extraction, which solves the problem of single entity overlap in the triples. Then, We divide the tail entity extraction into three parallel extraction sub-processes to solve entity pair overlap problem of triples, that is the relation overlap problem. Finally, We transform each extraction sub-process into sequence tag task. We evaluate our model on the New York Times (NYT) dataset and achieve overwhelming results compared with most of the current models, Precise =0.870, Recall = 0.851, and F1 = 0.860. The experimental results show that our model is effective in dealing with triples overlap problem.","PeriodicalId":423182,"journal":{"name":"2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121626261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Research on Rumor Propagation Simulation Based on Behavior-Attribute 基于行为属性的谣言传播仿真研究

2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC) Pub Date : 2020-07-01 DOI: 10.1109/DSC50466.2020.00041

Hailiang Chen, Bin Chen, Chuan Ai, Mengna Zhu, Kaisheng Lai, Lingnan He

引用次数: 0