首页 > 最新文献

Applied Computing Review最新文献

英文 中文
MUTUAL: Multi-Domain Sentiment Classification via Uncertainty Sampling MUTUAL:基于不确定性采样的多领域情感分类
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577765
K. Katsarou, Roxana Jeney, K. Stefanidis
Multi-domain sentiment classification trains a classifier using multiple domains and then tests the classifier on one of the domains. Importantly, no domain is assumed to have sufficient labeled data; instead, the goal is leveraging information between domains, making multi-domain sentiment classification a very realistic scenario. Typically, labeled data is costly because humans must classify it manually. In this context, we propose the MUTUAL approach that learns general and domain-specific sentence embeddings that are also context-aware due to the attention mechanism. In this work, we propose using a stacked BiLSTM-based Autoencoder with an attention mechanism to generate the two above-mentioned types of sentence embeddings. Then, using the Jensen-Shannon (JS) distance, the general sentence embeddings of the four most similar domains to the target domain are selected. The selected general sentence embeddings and the domain-specific embeddings are concatenated and fed into a dense layer for training. Evaluation results on public datasets with 16 different domains demonstrate the efficiency of our model. In addition, we propose an active learning algorithm that first applies the elliptic envelope for outlier removal to a pool of unlabeled data that the MUTUAL model then classifies. Next, the most uncertain data points are selected to be labeled based on the least confidence metric. The experiments show higher accuracy for querying 38% of the original data than random sampling.
多领域情感分类利用多个领域训练分类器,然后在其中一个领域上对分类器进行测试。重要的是,没有假设领域有足够的标记数据;相反,目标是利用域之间的信息,使多域情感分类成为一个非常现实的场景。通常,标记数据的成本很高,因为人类必须手动对其进行分类。在这种情况下,我们提出了MUTUAL方法,该方法学习一般和特定领域的句子嵌入,由于注意机制,它们也具有上下文感知能力。在这项工作中,我们提出使用一种带有注意机制的基于堆叠bilstm的自动编码器来生成上述两种类型的句子嵌入。然后,利用Jensen-Shannon (JS)距离,选择与目标域最相似的4个域的一般句子嵌入。将选择的一般句子嵌入和特定领域嵌入连接并馈送到密集层中进行训练。在16个不同领域的公共数据集上的评估结果证明了该模型的有效性。此外,我们提出了一种主动学习算法,该算法首先将椭圆包络用于异常值去除,然后对MUTUAL模型进行分类的未标记数据池进行分类。其次,选择最不确定的数据点,根据最小置信度度量进行标记。实验表明,与随机抽样相比,对原始数据的查询精度提高了38%。
{"title":"MUTUAL: Multi-Domain Sentiment Classification via Uncertainty Sampling","authors":"K. Katsarou, Roxana Jeney, K. Stefanidis","doi":"10.1145/3555776.3577765","DOIUrl":"https://doi.org/10.1145/3555776.3577765","url":null,"abstract":"Multi-domain sentiment classification trains a classifier using multiple domains and then tests the classifier on one of the domains. Importantly, no domain is assumed to have sufficient labeled data; instead, the goal is leveraging information between domains, making multi-domain sentiment classification a very realistic scenario. Typically, labeled data is costly because humans must classify it manually. In this context, we propose the MUTUAL approach that learns general and domain-specific sentence embeddings that are also context-aware due to the attention mechanism. In this work, we propose using a stacked BiLSTM-based Autoencoder with an attention mechanism to generate the two above-mentioned types of sentence embeddings. Then, using the Jensen-Shannon (JS) distance, the general sentence embeddings of the four most similar domains to the target domain are selected. The selected general sentence embeddings and the domain-specific embeddings are concatenated and fed into a dense layer for training. Evaluation results on public datasets with 16 different domains demonstrate the efficiency of our model. In addition, we propose an active learning algorithm that first applies the elliptic envelope for outlier removal to a pool of unlabeled data that the MUTUAL model then classifies. Next, the most uncertain data points are selected to be labeled based on the least confidence metric. The experiments show higher accuracy for querying 38% of the original data than random sampling.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89737340","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
Personalized Graph Attention Network for Multivariate Time-series Change Analysis: A Case Study on Long-term Maternal Monitoring 多变量时间序列变化分析的个性化图关注网络——以长期产妇监测为例
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577675
Yuning Wang, I. Azimi, M. Feli, A. Rahmani, P. Liljeberg
Internet-of-Things-based systems have recently emerged, enabling long-term health monitoring systems for the daily activities of individuals. The data collected from such systems are multivariate and longitudinal, which call for tailored analysis techniques to extract the trends and abnormalities in the monitoring. Different methods in the literature have been proposed to identify trends in data. However, they do not include the time dependency and cannot distinguish changes in long-term health data. Moreover, their evaluations are limited to lab settings or short-term analysis. Long-term health monitoring applications require a modeling technique to merge the multisensory data into a meaningful indicator. In this paper, we propose a personalized neural network method to track changes and abnormalities in multivariate health data. Our proposed method leverages convolutional and graph attention layers to produce personalized scores indicating the abnormality level (i.e., deviations from the baseline) of users' data throughout the monitoring. We implement and evaluate the proposed method via a case study on long-term maternal health monitoring. Sleep and stress of pregnant women are remotely monitored using a smartwatch and a mobile application during pregnancy and 3-months postpartum. Our analysis includes 46 women. We build personalized sleep and stress models for each individual using the data from the beginning of the monitoring. Then, we compare the two groups by measuring the data variations. The abnormality scores produced by the proposed method are compared with the findings from the self-report questionnaire data collected in the monitoring and abnormality scores generated by an autoencoder method. The proposed method outperforms the baseline methods in exploring the changes between high-risk and low-risk pregnancy groups. The proposed method's scores also show correlations with the self-report data. Consequently, the results indicate that the proposed method effectively detects the abnormality in multivariate long-term health monitoring.
最近出现了基于物联网的系统,使个人日常活动的长期健康监测系统成为可能。从这些系统收集的数据是多变量的和纵向的,这就需要有针对性的分析技术来提取监测中的趋势和异常。文献中提出了不同的方法来确定数据的趋势。然而,它们不包括时间依赖性,不能区分长期健康数据的变化。此外,他们的评估仅限于实验室环境或短期分析。长期健康监测应用需要一种建模技术,将多感官数据合并为有意义的指标。在本文中,我们提出了一种个性化的神经网络方法来跟踪多变量健康数据的变化和异常。我们提出的方法利用卷积和图形关注层来生成个性化分数,表明在整个监测过程中用户数据的异常水平(即与基线的偏差)。我们通过一个关于长期产妇健康监测的案例研究来实施和评估拟议的方法。在怀孕期间和产后3个月,通过智能手表和移动应用程序远程监测孕妇的睡眠和压力。我们的分析包括46名女性。我们利用监测开始时的数据为每个人建立个性化的睡眠和压力模型。然后,我们通过测量数据变化来比较两组。将该方法生成的异常分数与监测中收集的自我报告问卷数据和自动编码器方法生成的异常分数进行比较。该方法在探索高危和低危妊娠组之间的变化方面优于基线方法。该方法的得分也显示出与自我报告数据的相关性。结果表明,该方法能有效地检测出多变量长期健康监测中的异常。
{"title":"Personalized Graph Attention Network for Multivariate Time-series Change Analysis: A Case Study on Long-term Maternal Monitoring","authors":"Yuning Wang, I. Azimi, M. Feli, A. Rahmani, P. Liljeberg","doi":"10.1145/3555776.3577675","DOIUrl":"https://doi.org/10.1145/3555776.3577675","url":null,"abstract":"Internet-of-Things-based systems have recently emerged, enabling long-term health monitoring systems for the daily activities of individuals. The data collected from such systems are multivariate and longitudinal, which call for tailored analysis techniques to extract the trends and abnormalities in the monitoring. Different methods in the literature have been proposed to identify trends in data. However, they do not include the time dependency and cannot distinguish changes in long-term health data. Moreover, their evaluations are limited to lab settings or short-term analysis. Long-term health monitoring applications require a modeling technique to merge the multisensory data into a meaningful indicator. In this paper, we propose a personalized neural network method to track changes and abnormalities in multivariate health data. Our proposed method leverages convolutional and graph attention layers to produce personalized scores indicating the abnormality level (i.e., deviations from the baseline) of users' data throughout the monitoring. We implement and evaluate the proposed method via a case study on long-term maternal health monitoring. Sleep and stress of pregnant women are remotely monitored using a smartwatch and a mobile application during pregnancy and 3-months postpartum. Our analysis includes 46 women. We build personalized sleep and stress models for each individual using the data from the beginning of the monitoring. Then, we compare the two groups by measuring the data variations. The abnormality scores produced by the proposed method are compared with the findings from the self-report questionnaire data collected in the monitoring and abnormality scores generated by an autoencoder method. The proposed method outperforms the baseline methods in exploring the changes between high-risk and low-risk pregnancy groups. The proposed method's scores also show correlations with the self-report data. Consequently, the results indicate that the proposed method effectively detects the abnormality in multivariate long-term health monitoring.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85777674","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
Realism versus Performance for Adversarial Examples Against DL-based NIDS 针对基于dl的NIDS的对抗性示例的现实性与性能
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577671
Huda Ali Alatwi, C. Morisset
The application of deep learning-based (DL) network intrusion detection systems (NIDS) enables effective automated detection of cyberattacks. Such models can extract valuable features from high-dimensional and heterogeneous network traffic with minimal feature engineering and provide high accuracy detection rates. However, it has been shown that DL can be vulnerable to adversarial examples (AEs), which mislead classification decisions at inference time, and several works have shown that AEs are indeed a threat against DL-based NIDS. In this work, we argue that these threats are not necessarily realistic. Indeed, some general techniques used to generate AE manipulate features in a way that would be inconsistent with actual network traffic. In this paper, we first implement the main AE attacks selected from the literature (FGSM, BIM, PGD, NewtonFool, CW, DeepFool, EN, Boundary, HSJ, ZOO) for two different datasets (WSN-DS and BoT-IoT) and we compare their relative performance. We then analyze the perturbation generated by these attacks and use the metrics to establish a notion of "attack unrealism". We conclude that, for these datasets, some of these attacks are performant but not realistic.
基于深度学习(DL)的网络入侵检测系统(NIDS)的应用能够有效地自动检测网络攻击。该模型可以以最小的特征工程从高维异构网络流量中提取有价值的特征,并提供较高的准确率检测率。然而,已有研究表明,深度学习可能容易受到对抗性示例(AEs)的影响,这些示例会在推理时误导分类决策,并且一些研究表明,AEs确实是对基于DL的NIDS的威胁。在这项工作中,我们认为这些威胁并不一定是现实的。实际上,一些用于生成AE的通用技术以一种与实际网络流量不一致的方式操作特征。在本文中,我们首先针对两个不同的数据集(WSN-DS和BoT-IoT)实现了从文献中选择的主要AE攻击(FGSM, BIM, PGD, NewtonFool, CW, DeepFool, EN, Boundary, HSJ, ZOO),并比较了它们的相对性能。然后,我们分析由这些攻击产生的扰动,并使用度量来建立“攻击非现实性”的概念。我们得出的结论是,对于这些数据集,其中一些攻击是有效的,但不现实。
{"title":"Realism versus Performance for Adversarial Examples Against DL-based NIDS","authors":"Huda Ali Alatwi, C. Morisset","doi":"10.1145/3555776.3577671","DOIUrl":"https://doi.org/10.1145/3555776.3577671","url":null,"abstract":"The application of deep learning-based (DL) network intrusion detection systems (NIDS) enables effective automated detection of cyberattacks. Such models can extract valuable features from high-dimensional and heterogeneous network traffic with minimal feature engineering and provide high accuracy detection rates. However, it has been shown that DL can be vulnerable to adversarial examples (AEs), which mislead classification decisions at inference time, and several works have shown that AEs are indeed a threat against DL-based NIDS. In this work, we argue that these threats are not necessarily realistic. Indeed, some general techniques used to generate AE manipulate features in a way that would be inconsistent with actual network traffic. In this paper, we first implement the main AE attacks selected from the literature (FGSM, BIM, PGD, NewtonFool, CW, DeepFool, EN, Boundary, HSJ, ZOO) for two different datasets (WSN-DS and BoT-IoT) and we compare their relative performance. We then analyze the perturbation generated by these attacks and use the metrics to establish a notion of \"attack unrealism\". We conclude that, for these datasets, some of these attacks are performant but not realistic.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86228950","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
Improving the Quality of Public Transportation by Dynamically Adjusting the Bus Departure Time 动态调整公交发车时间提高公共交通质量
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577596
Shuheng Cao, S. Thamrin, Arbee L. P. Chen
Nowadays, more and more smart cities around the world are being built. As a part of the smart city, intelligent public transportation plays a very important role. Improving the quality of public transportation by reducing crowdedness and total transit time is a critical issue. To this end, we propose a bus operation prediction model based on deep learning techniques, and use this model to dynamically adjust the bus departure time to improve the bus service quality. Specifically, we first combine bus fare card data and open data, such as weather conditions and traffic accidents, to build models for predicting the number of passengers who board/alight the bus at a stop, the boarding and alighting time, and the bus running time between stops. Then we combine these models to predict the operation of the bus for deciding the best bus departure time within the bus departure interval. Experimental results on real-world data of Taichung City bus route #300 show that our approach to deciding the bus departure time is effective for improving its service quality.
如今,世界各地正在建设越来越多的智慧城市。作为智慧城市的一部分,智能公共交通扮演着非常重要的角色。通过减少拥挤和总运输时间来提高公共交通的质量是一个关键问题。为此,我们提出了一种基于深度学习技术的公交运行预测模型,并利用该模型动态调整公交发车时间,以提高公交服务质量。具体来说,我们首先将公交车费卡数据与开放数据(如天气条件和交通事故)结合起来,建立模型来预测在一个站点上/下公交车的乘客数量、上/下公交车的时间以及站点之间的公交车运行时间。然后结合这些模型对公交运行进行预测,以确定公交发车间隔内的最佳发车时间。台中市巴士300号线实际数据的实验结果显示,本方法能有效地决定巴士出发时间,提高巴士服务品质。
{"title":"Improving the Quality of Public Transportation by Dynamically Adjusting the Bus Departure Time","authors":"Shuheng Cao, S. Thamrin, Arbee L. P. Chen","doi":"10.1145/3555776.3577596","DOIUrl":"https://doi.org/10.1145/3555776.3577596","url":null,"abstract":"Nowadays, more and more smart cities around the world are being built. As a part of the smart city, intelligent public transportation plays a very important role. Improving the quality of public transportation by reducing crowdedness and total transit time is a critical issue. To this end, we propose a bus operation prediction model based on deep learning techniques, and use this model to dynamically adjust the bus departure time to improve the bus service quality. Specifically, we first combine bus fare card data and open data, such as weather conditions and traffic accidents, to build models for predicting the number of passengers who board/alight the bus at a stop, the boarding and alighting time, and the bus running time between stops. Then we combine these models to predict the operation of the bus for deciding the best bus departure time within the bus departure interval. Experimental results on real-world data of Taichung City bus route #300 show that our approach to deciding the bus departure time is effective for improving its service quality.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86297252","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 Performant and Secure Single Sign-On System Using Microservices 基于微服务的高性能安全单点登录系统
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577869
Mahyar Tourchi Moghaddam, Andreas Edal Pedersen, William Walter Lillebroe Bolding, T. Worm
The Single Sign-On (SSO) method eases the authentication and authorization process. The solution substantially impacts the users' experience since they only need to authenticate once to access multiple services without re-authenticating. This paper adopts an incremental prototyping approach to develop an SSO system. The research reveals that while SSO improves users' quality of experience, it could imply performance and security issues if traditional architectures are adopted. Thus, a Microservices-based approach with containerization is subsequently proposed to overcome SSO's quality issues in practice. The SSO system is containerized using Docker and managed using Docker Compose. The results show a significant performance and security improvement.
SSO (Single Sign-On)简化了认证和授权过程。该解决方案极大地影响了用户的体验,因为他们只需要验证一次即可访问多个服务,而无需重新验证。本文采用增量原型方法开发单点登录系统。研究表明,虽然SSO提高了用户的体验质量,但如果采用传统架构,它可能意味着性能和安全问题。因此,随后提出了一种基于微服务的容器化方法,以克服SSO在实践中的质量问题。SSO系统使用Docker进行容器化,并使用Docker Compose进行管理。结果显示了显著的性能和安全性改进。
{"title":"A Performant and Secure Single Sign-On System Using Microservices","authors":"Mahyar Tourchi Moghaddam, Andreas Edal Pedersen, William Walter Lillebroe Bolding, T. Worm","doi":"10.1145/3555776.3577869","DOIUrl":"https://doi.org/10.1145/3555776.3577869","url":null,"abstract":"The Single Sign-On (SSO) method eases the authentication and authorization process. The solution substantially impacts the users' experience since they only need to authenticate once to access multiple services without re-authenticating. This paper adopts an incremental prototyping approach to develop an SSO system. The research reveals that while SSO improves users' quality of experience, it could imply performance and security issues if traditional architectures are adopted. Thus, a Microservices-based approach with containerization is subsequently proposed to overcome SSO's quality issues in practice. The SSO system is containerized using Docker and managed using Docker Compose. The results show a significant performance and security improvement.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87396157","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
DISO: A Domain Ontology for Modeling Dislocations in Crystalline Materials 晶体材料位错建模的领域本体
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3578739
Ahmad Zainul Ihsan, S. Fathalla, S. Sandfeld
Crystalline materials, such as metals and semiconductors, nearly always contain a special defect type called dislocation. This defect decisively determines many important material properties, e.g., strength, fracture toughness, or ductility. Over the past years, significant effort has been put into understanding dislocation behavior across different length scales via experimental characterization techniques and simulations. This paper introduces the dislocation ontology (DISO), which defines the concepts and relationships related to linear defects in crystalline materials. We developed DISO using a top-down approach in which we start defining the most general concepts in the dislocation domain and subsequent specialization of them. DISO is published through a persistent URL following W3C best practices for publishing Linked Data. Two potential use cases for DISO are presented to illustrate its usefulness in the dislocation dynamics domain. The evaluation of the ontology is performed in two directions, evaluating the success of the ontology in modeling a real-world domain and the richness of the ontology.
晶体材料,如金属和半导体,几乎总是包含一种特殊的缺陷类型,称为位错。这种缺陷决定性地决定了许多重要的材料性能,例如强度、断裂韧性或延展性。在过去的几年中,通过实验表征技术和模拟,已经投入了大量的努力来理解不同长度尺度上的位错行为。本文介绍了位错本体(DISO),它定义了晶体材料中线性缺陷的相关概念和关系。我们采用自上而下的方法开发了DISO,在这种方法中,我们开始定义位错域中最一般的概念,并随后对它们进行专业化。DISO遵循发布关联数据的W3C最佳实践,通过持久URL发布。提出了DISO的两个潜在用例来说明它在位错动力学领域的有用性。对本体的评价从两个方面进行,即评价本体在现实世界领域建模的成功程度和本体的丰富性。
{"title":"DISO: A Domain Ontology for Modeling Dislocations in Crystalline Materials","authors":"Ahmad Zainul Ihsan, S. Fathalla, S. Sandfeld","doi":"10.1145/3555776.3578739","DOIUrl":"https://doi.org/10.1145/3555776.3578739","url":null,"abstract":"Crystalline materials, such as metals and semiconductors, nearly always contain a special defect type called dislocation. This defect decisively determines many important material properties, e.g., strength, fracture toughness, or ductility. Over the past years, significant effort has been put into understanding dislocation behavior across different length scales via experimental characterization techniques and simulations. This paper introduces the dislocation ontology (DISO), which defines the concepts and relationships related to linear defects in crystalline materials. We developed DISO using a top-down approach in which we start defining the most general concepts in the dislocation domain and subsequent specialization of them. DISO is published through a persistent URL following W3C best practices for publishing Linked Data. Two potential use cases for DISO are presented to illustrate its usefulness in the dislocation dynamics domain. The evaluation of the ontology is performed in two directions, evaluating the success of the ontology in modeling a real-world domain and the richness of the ontology.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85565649","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: 2
Sec2vec: Anomaly Detection in HTTP Traffic and Malicious URLs Sec2vec: HTTP流量和恶意url的异常检测
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577663
Mateusz Gniewkowski, H. Maciejewski, T. Surmacz, Wiktor Walentynowicz
In this paper, we show how methods known from Natural Language Processing (NLP) can be used to detect anomalies in HTTP requests and malicious URLs. Most of the current solutions focusing on a similar problem are either rule-based or trained using manually selected features. Modern NLP methods, however, have great potential in capturing a deep understanding of samples and therefore improving the classification results. Other methods, which rely on a similar idea, often ignore the interpretability of the results, which is so important in machine learning. We are trying to fill this gap. In addition, we show to what extent the proposed solutions are resistant to concept drift. In our work, we compare three different vectorization methods: simple BoW, fastText, and the current state-of-the-art language model RoBERTa. The obtained vectors are later used in the classification task. In order to explain our results, we utilize the SHAP method. We evaluate the feasibility of our methods on four different datasets: CSIC2010, UNSW-NB15, MALICIOUSURL, and ISCX-URL2016. The first two are related to HTTP traffic, the other two contain malicious URLs. The results we show are comparable to others or better, and most importantly - interpretable.
在本文中,我们展示了如何使用自然语言处理(NLP)中已知的方法来检测HTTP请求和恶意url中的异常情况。目前针对类似问题的大多数解决方案要么是基于规则的,要么是使用手动选择的特征进行训练的。然而,现代NLP方法在获取对样本的深入理解从而改进分类结果方面具有很大的潜力。其他依赖于类似想法的方法往往忽略了结果的可解释性,而这在机器学习中非常重要。我们正在努力填补这一空白。此外,我们还展示了所提出的解决方案在多大程度上能够抵抗概念漂移。在我们的工作中,我们比较了三种不同的矢量化方法:简单的BoW、fastText和当前最先进的语言模型RoBERTa。得到的向量稍后用于分类任务。为了解释我们的结果,我们使用了SHAP方法。我们评估了我们的方法在四个不同数据集上的可行性:CSIC2010、UNSW-NB15、MALICIOUSURL和ISCX-URL2016。前两个与HTTP流量有关,另外两个包含恶意url。我们展示的结果与他人相当或更好,最重要的是-可解释。
{"title":"Sec2vec: Anomaly Detection in HTTP Traffic and Malicious URLs","authors":"Mateusz Gniewkowski, H. Maciejewski, T. Surmacz, Wiktor Walentynowicz","doi":"10.1145/3555776.3577663","DOIUrl":"https://doi.org/10.1145/3555776.3577663","url":null,"abstract":"In this paper, we show how methods known from Natural Language Processing (NLP) can be used to detect anomalies in HTTP requests and malicious URLs. Most of the current solutions focusing on a similar problem are either rule-based or trained using manually selected features. Modern NLP methods, however, have great potential in capturing a deep understanding of samples and therefore improving the classification results. Other methods, which rely on a similar idea, often ignore the interpretability of the results, which is so important in machine learning. We are trying to fill this gap. In addition, we show to what extent the proposed solutions are resistant to concept drift. In our work, we compare three different vectorization methods: simple BoW, fastText, and the current state-of-the-art language model RoBERTa. The obtained vectors are later used in the classification task. In order to explain our results, we utilize the SHAP method. We evaluate the feasibility of our methods on four different datasets: CSIC2010, UNSW-NB15, MALICIOUSURL, and ISCX-URL2016. The first two are related to HTTP traffic, the other two contain malicious URLs. The results we show are comparable to others or better, and most importantly - interpretable.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79851654","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
MP-DDPG: Optimal Latency-Energy Dynamic Offloading Scheme in Collaborative Cloud Networks 协同云网络中最优延迟-能量动态卸载方案
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577767
Jui Mhatre, Ahyoung Lee
Growing technologies like virtualization and artificial intelligence have become more popular on mobile devices. But lack of resources faced for processing these applications is still major hurdle. Collaborative edge and cloud computing are one of the solutions to this problem. We have proposed a multi-period deep deterministic policy gradient (MP-DDPG) algorithm to find an optimal offloading policy by partitioning the task and offloading it to the collaborative cloud and edge network to reduce energy consumption. Our results show that MP-DDPG achieves the minimum latency and energy consumption in the collaborative cloud network.
像虚拟化和人工智能这样的新兴技术在移动设备上变得越来越流行。但缺乏处理这些申请所需的资源仍然是主要障碍。协作边缘和云计算是这个问题的解决方案之一。我们提出了一种多周期深度确定性策略梯度(MP-DDPG)算法,通过划分任务并将其卸载到协作云和边缘网络来寻找最优卸载策略,以降低能耗。结果表明,MP-DDPG在协同云网络中实现了最小的延迟和能耗。
{"title":"MP-DDPG: Optimal Latency-Energy Dynamic Offloading Scheme in Collaborative Cloud Networks","authors":"Jui Mhatre, Ahyoung Lee","doi":"10.1145/3555776.3577767","DOIUrl":"https://doi.org/10.1145/3555776.3577767","url":null,"abstract":"Growing technologies like virtualization and artificial intelligence have become more popular on mobile devices. But lack of resources faced for processing these applications is still major hurdle. Collaborative edge and cloud computing are one of the solutions to this problem. We have proposed a multi-period deep deterministic policy gradient (MP-DDPG) algorithm to find an optimal offloading policy by partitioning the task and offloading it to the collaborative cloud and edge network to reduce energy consumption. Our results show that MP-DDPG achieves the minimum latency and energy consumption in the collaborative cloud network.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80246251","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
Scalable Coercion-Resistant E-Voting under Weaker Trust Assumptions 弱信任假设下的可伸缩抗强制电子投票
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3578730
Thomas Haines, Johannes Müller, Iñigo Querejeta-Azurmendi
Electronic voting (e-voting) is regularly used in many countries and organizations for legally binding elections. In order to conduct such elections securely, numerous e-voting systems have been proposed over the last few decades. Notably, some of these systems were designed to provide coercion-resistance. This property protects against potential adversaries trying to swing an election by coercing voters. Despite the multitude of existing coercion-resistant e-voting systems, to date, only few of them can handle large-scale Internet elections efficiently. One of these systems, VoteAgain (USENIX Security 2020), was originally claimed secure under similar trust assumptions to state-of-the-art e-voting systems without coercion-resistance. In this work, we review VoteAgain's security properties. We discover that, unlike originally claimed, VoteAgain is no more secure than a trivial voting system with a completely trusted election authority. In order to mitigate this issue, we propose a variant of VoteAgain which effectively mitigates trust on the election authorities and, at the same time, preserves VoteAgain's usability and efficiency. Altogether, our findings bring the state of science one step closer to the goal of scalable coercion-resistant e-voting being secure under reasonable trust assumptions.
电子投票(e-voting)在许多国家和组织中经常用于具有法律约束力的选举。为了安全地进行这样的选举,在过去的几十年里,人们提出了许多电子投票系统。值得注意的是,其中一些系统旨在提供抗矫顽力。这一属性可以防止潜在的对手试图通过胁迫选民来影响选举。尽管现有的电子投票系统众多,但迄今为止,只有少数能够有效地处理大规模的互联网选举。其中一个系统VoteAgain (USENIX Security 2020)最初被声称在与最先进的电子投票系统类似的信任假设下是安全的,没有强制阻力。在本文中,我们将回顾VoteAgain的安全属性。我们发现,与最初声称的不同,VoteAgain并不比一个具有完全可信的选举机构的微不足道的投票系统更安全。为了缓解这个问题,我们提出了一个VoteAgain的变体,它有效地减轻了对选举当局的信任,同时保持了VoteAgain的可用性和效率。总而言之,我们的研究结果使科学状态更接近可扩展的抗强制电子投票在合理信任假设下是安全的目标。
{"title":"Scalable Coercion-Resistant E-Voting under Weaker Trust Assumptions","authors":"Thomas Haines, Johannes Müller, Iñigo Querejeta-Azurmendi","doi":"10.1145/3555776.3578730","DOIUrl":"https://doi.org/10.1145/3555776.3578730","url":null,"abstract":"Electronic voting (e-voting) is regularly used in many countries and organizations for legally binding elections. In order to conduct such elections securely, numerous e-voting systems have been proposed over the last few decades. Notably, some of these systems were designed to provide coercion-resistance. This property protects against potential adversaries trying to swing an election by coercing voters. Despite the multitude of existing coercion-resistant e-voting systems, to date, only few of them can handle large-scale Internet elections efficiently. One of these systems, VoteAgain (USENIX Security 2020), was originally claimed secure under similar trust assumptions to state-of-the-art e-voting systems without coercion-resistance. In this work, we review VoteAgain's security properties. We discover that, unlike originally claimed, VoteAgain is no more secure than a trivial voting system with a completely trusted election authority. In order to mitigate this issue, we propose a variant of VoteAgain which effectively mitigates trust on the election authorities and, at the same time, preserves VoteAgain's usability and efficiency. Altogether, our findings bring the state of science one step closer to the goal of scalable coercion-resistant e-voting being secure under reasonable trust assumptions.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89267605","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
Alleviating High Gas Costs by Secure and Trustless Off-chain Execution of Smart Contracts 通过安全、无信任的智能合约链下执行来降低高昂的天然气成本
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577833
Soroush Farokhnia, Amir Kafshdar Goharshady
Smart contracts are programs that are executed on the blockchain and can hold, manage and transfer assets in the form of cryptocurrencies. The contract's execution is then performed on-chain and is subject to consensus, i.e. every node on the blockchain network has to run the function calls and keep track of their side-effects including updates to the balances and contract's storage. The notion of gas is introduced in most programmable blockchains, which prevents DoS attacks from malicious parties who might try to slow down the network by performing time-consuming and resource-heavy computations. While the gas idea has largely succeeded in its goal of avoiding DoS attacks, the resulting fees are extremely high. For example, in June-September 2022, on Ethereum alone, there has been an average total gas usage of 2,706.8 ETH ≈ 3,938,749 USD per day. We propose a protocol for alleviating these costs by moving most of the computation off-chain while preserving enough data on-chain to guarantee an implicit consensus about the contract state and ownership of funds in case of dishonest parties. We perform extensive experiments over 3,330 real-world Solidity contracts that were involved in 327,132 transactions in June-September 2022 on Ethereum and show that our approach reduces their gas usage by 40.09 percent, which amounts to a whopping 442,651 USD.
智能合约是在区块链上执行的程序,可以以加密货币的形式持有、管理和转移资产。然后,合约的执行在链上执行,并受到共识的约束,即区块链网络上的每个节点都必须运行函数调用,并跟踪其副作用,包括更新余额和合约的存储。大多数可编程区块链中都引入了gas的概念,这可以防止恶意方的DoS攻击,恶意方可能会通过执行耗时且资源繁重的计算来减慢网络速度。虽然gas的想法在很大程度上成功地避免了DoS攻击,但由此产生的费用非常高。例如,在2022年6月至9月期间,仅在以太坊上,平均每天的总天然气使用量为2,706.8 ETH≈3,938,749美元。我们提出了一种协议,通过将大部分计算移到链下,同时在链上保留足够的数据,以保证在不诚实的各方的情况下,对合同状态和资金所有权达成隐含共识,从而降低这些成本。我们对3330份真实世界的Solidity合约进行了广泛的实验,这些合约在2022年6月至9月期间在以太坊上进行了327,132笔交易,并表明我们的方法将他们的天然气使用量减少了40.09%,这相当于高达442,651美元。
{"title":"Alleviating High Gas Costs by Secure and Trustless Off-chain Execution of Smart Contracts","authors":"Soroush Farokhnia, Amir Kafshdar Goharshady","doi":"10.1145/3555776.3577833","DOIUrl":"https://doi.org/10.1145/3555776.3577833","url":null,"abstract":"Smart contracts are programs that are executed on the blockchain and can hold, manage and transfer assets in the form of cryptocurrencies. The contract's execution is then performed on-chain and is subject to consensus, i.e. every node on the blockchain network has to run the function calls and keep track of their side-effects including updates to the balances and contract's storage. The notion of gas is introduced in most programmable blockchains, which prevents DoS attacks from malicious parties who might try to slow down the network by performing time-consuming and resource-heavy computations. While the gas idea has largely succeeded in its goal of avoiding DoS attacks, the resulting fees are extremely high. For example, in June-September 2022, on Ethereum alone, there has been an average total gas usage of 2,706.8 ETH ≈ 3,938,749 USD per day. We propose a protocol for alleviating these costs by moving most of the computation off-chain while preserving enough data on-chain to guarantee an implicit consensus about the contract state and ownership of funds in case of dishonest parties. We perform extensive experiments over 3,330 real-world Solidity contracts that were involved in 327,132 transactions in June-September 2022 on Ethereum and show that our approach reduces their gas usage by 40.09 percent, which amounts to a whopping 442,651 USD.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77813297","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
期刊
Applied Computing Review
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1