scholarly journals Autenticação Contínua de Usuários Utilizando Contadores de Desempenho do Sistema Operacional

2019 ◽  
Author(s):  
César Andrade ◽  
Paulo Henrique Gonçalves ◽  
Hendrio Bragança ◽  
Eduardo Souto

Computer authentication systems based on login and password have been vulnerable to the action of unauthorized users. Currently, authentication techniques based on behavioral models predominantly use information extracted from mouse and/or keyboard to authenticate users. Operating system performance indicators can be used as an alternative. This work proposes an approach using data from performance indicators such as source data, CNN/LSTM networks for data classification, and reliability-based assessment methodology for the purpose of authenticating the user on an ongoing basis. The results obtained demonstrate the feasibility of using these attributes as the origin of the data to define a behavioral model. The best result obtained in this research is that 100% of genuine users are never inadvertently blocked and 100% of the imposters are detected after the average of three actions. Sistemas de autenticação de computadores baseados em credencias de contas (e.g. login e senha) têm sido vulneráveis à ação de usuários não autorizados. Atualmente, as técnicas de autenticação baseadas em modelos comportamentais predominantemente usam informações extraídas de mouse e/ou teclado para autenticar os usuários. Contadores de desempenho de sistema operacional podem ser utilizadas como alternativa. Este trabalho propõe uma abordagem utilizando dados de contadores de desempenho como dados de origem, redes CNN/LSTM para classificação dos dados e metodologia de avaliação baseada em nível de confiança com o propósito de autenticar o usuário de forma contínua. Os resultados obtidos demonstram a viabilidade do uso destes atributos como origem dos dados para definição de modelo comportamental. O melhor resultado obtido nesta pesquisa é que 100% dos usuários genuínos nunca são bloqueados inadvertidamente e 100% dos impostores são detectados após a média de três ações.

Author(s):  
Eric Coatane´a ◽  
Tuomas Ritola ◽  
Irem Y. Tumer ◽  
David Jensen

In this paper, a design-stage failure identification framework is proposed using a modeling and simulation approach based on Dimensional Analysis and qualitative physics. The proposed framework is intended to provide a new approach to model the behavior in the Functional-Failure Identification and Propagation (FFIP) framework, which estimates potential faults and their propagation paths under critical event scenarios. The initial FFIP framework is based on combining hierarchical system models of functionality and configuration, with behavioral simulation and qualitative reasoning. This paper proposes to develop a behavioral model derived from information available at the configuration level. Specifically, the new behavioral model uses design variables, which are associated with units and quantities (i.e., Mass, Length, Time, etc…). The proposed framework continues the work to allow the analysis of functional failures and fault propagation at a highly abstract system concept level before any potentially high-cost design commitments are made. The main contribution in this paper consists of developing component behavioral models based on the combination of fundamental design variables used to describe components and their units or quantities, more precisely describing components’ behavior.


Author(s):  
Daniel F. Silva ◽  
Alexander Vinel ◽  
Bekircan Kirkici

With recent advances in mobile technology, public transit agencies around the world have started actively experimenting with new transportation modes, many of which can be characterized as on-demand public transit. Design and efficient operation of such systems can be particularly challenging, because they often need to carefully balance demand volume with resource availability. We propose a family of models for on-demand public transit that combine a continuous approximation methodology with a Markov process. Our goal is to develop a tractable method to evaluate and predict system performance, specifically focusing on obtaining the probability distribution of performance metrics. This information can then be used in capital planning, such as fleet sizing, contracting, and driver scheduling, among other things. We present the analytical solution for a stylized single-vehicle model of first-mile operation. Then, we describe several extensions to the base model, including two approaches for the multivehicle case. We use computational experiments to illustrate the effects of the inputs on the performance metrics and to compare different modes of transit. Finally, we include a case study, using data collected from a real-world pilot on-demand public transit project in a major U.S. metropolitan area, to showcase how the proposed model can be used to predict system performance and support decision making.


2021 ◽  
Vol 12 (4) ◽  
pp. 185
Author(s):  
Wujian Yang ◽  
Jianghao Dong ◽  
Yuke Ren

Hydrogen energy vehicles are being increasingly widely used. To ensure the safety of hydrogenation stations, research into the detection of hydrogen leaks is required. Offline analysis using data machine learning is achieved using Spark SQL and Spark MLlib technology. In this study, to determine the safety status of a hydrogen refueling station, we used multiple algorithm models to perform calculation and analysis: a multi-source data association prediction algorithm, a random gradient descent algorithm, a deep neural network optimization algorithm, and other algorithm models. We successfully analyzed the data, including the potential relationships, internal relationships, and operation laws between the data, to detect the safety statuses of hydrogen refueling stations.


Author(s):  
Nagaraj G Cholli ◽  
Srinivasan G N

A software aging in convoluted system refers to the situation where software degrades with span of time. This phenomenon, which may eventually lead to system performance degradation or crash/hang failure, is the result of depletion of operating system resources, data deception and numerical error assembly. A technique called software rejuvenation has been incorporated, which essentially involves periodic aborting an application or a system, flushing its intramural state and re-starting it. A main issue in rejuvenation is to discover ideal time to initiate software rejuvenation. Software rejuvenation is a proactive technique that allows preventing the occurrence of software failing. A novel approach called Smart interval and payload (SIP) policy is introduced to overcome all the hurdles in the present scenario based on Software Rejuvenation approaches. SIP policy accepts time from user and optimizes the rejuvenation time whenever workload is variable; otherwise the system is rejuvenated at its rejuvenation point. SIP policy avoids software failure and it helps to achieve high availability of convoluted system.


2018 ◽  
Vol 2018 (15) ◽  
pp. 1002-1006 ◽  
Author(s):  
Guilherme Dantas de Freitas ◽  
Boussaad Ismail ◽  
Alberto Bertinato ◽  
Bertrand Raison ◽  
Eric Niel ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document