| 1. |
- Jabeen, Gul, et al.
(författare)
-
Machine learning techniques for software vulnerability prediction : a comparative study
- 2022
-
Ingår i: Applied intelligence (Boston). - : SPRINGER. - 0924-669X .- 1573-7497.
-
Tidskriftsartikel (refereegranskat)abstract
- Software vulnerabilities represent a major cause of security problems. Various vulnerability discovery models (VDMs) attempt to model the rate at which the vulnerabilities are discovered in a software. Although several VDMs have been proposed, not all of them are universally applicable. Also most of them seldom give accurate predictive results for every type of vulnerability dataset. The use of machine learning (ML) techniques has generally found success in a wide range of predictive tasks. Thus, in this paper, we conducted an empirical study on applying some well-known machine learning (ML) techniques as well as statistical techniques to predict the software vulnerabilities on a variety of datasets. The following ML techniques have been evaluated: cascade-forward back propagation neural network, feed-forward back propagation neural network, adaptive-neuro fuzzy inference system, multi-layer perceptron, support vector machine, bagging, M5Rrule, M5P and reduced error pruning tree. The following statistical techniques have been evaluated: Alhazmi-Malaiya model, linear regression and logistic regression model. The applicability of the techniques is examined using two separate approaches: goodness-of-fit to see how well the model tracks the data, and prediction capability using different criteria. It is observed that ML techniques show remarkable improvement in predicting the software vulnerabilities than the statistical vulnerability prediction models.
|
|
| 2. |
- Mehmood, M. A., et al.
(författare)
-
Automating Test Data Generation for Testing Context-Aware Applications
- 2018
-
Ingår i: Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS. - : IEEE Computer Society. - 9781538665640 ; , s. 104-108
-
Konferensbidrag (refereegranskat)abstract
- Context-aware applications are emerging applications in the modern era of computing. These applications can determine and adapt to situational context to provide better user experience. Testing these applications is not straightforward and poses several challenges such as developing context-aware test cases and generating test data etc. However, by employing model based testing technique, testing process for context-aware applications can be automated. To achieve maximum degree of automation, it is necessary to automate model transformation, test data generation and test cases execution. To execute test cases, test data is required and developing test data for context-aware applications is a challenging task. The aim of this study is to address this issue; thus, we propose automated test data generation for functional testing of context-aware applications. This automated test data generation can reduce testing time and cost, thus enabling test engineers to execute more testing cycles to attain higher degree of test coverage.
|
|
| 3. |
- Mehmood, M. A., et al.
(författare)
-
Transforming context-aware application development model into a testing model
- 2017
-
Ingår i: Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS. - : IEEE Computer Society. - 9781538645703 ; , s. 177-182
-
Konferensbidrag (refereegranskat)abstract
- Software testing aims at ensuring the quality of a software product. Context-aware applications are emerging applications that are capable to sense their environment and adapt to situational context to provide better user experience. Context-aware applications pose many challenges for software testing such as defining test adequacy criteria, generating test data, developing context-aware test cases etc. Test case generation process for context-aware applications can be automated using a model based testing technique. To attain this goal with maximum degree of automation, it is required to transform development model into a test model automatically. In this study, we propose a typecast of activity node of UML activity diagram, called Context-Aware Activity for modelling context-aware applications. We have also developed an approach for automatic transformation of the development model i.e., UML activity diagram with Context-aware Activity typecast into a testing model i.e. function nets. This testing model is used to automate test case generation and we have illustrated how to generate context-aware test cases using our proposed approach.
|
|
| 4. |
- Muellner, Nils, et al.
(författare)
-
Simulation-Based Safety Testing Brake-by-Wire
- 2017
-
Ingår i: Proceedings - 10th IEEE International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2017. - 9781509066766 ; , s. 61-64
-
Konferensbidrag (refereegranskat)abstract
- Mechanical systems in cars are replaced by electronic equivalents. To be authorized for the road, validation that the replacements are at least as good as the old systems is required. For electronic braking systems (brake-by-wire), this goodness translates to safety in terms of maintaining timing constraints. Yet, in the future, the safety of braking maneuvres will depend, not only, on electronic brakes, but also on cooperative driving maneuvres orchestrated among many cars. Connecting both brake-by-wire on the microscopic level with cooperative braking on the macroscopic level allows for determining safety on a broader scale, as both systems feed from the same resource: Time. This paper discusses work-in-progress, introducing and combining two threads: electronic brakes and cooperative braking. Discussing safety on two levels simultaneously motivates connecting a Simulink model of an electronic brake-by-wire system with the traffic simulator SUMO for conducting the required combined validation. How safe is a car in relation to a given maximal braking distance? What is the optimal distribution of reaction time between electronic brakes and cooperative braking? The validation focuses on non-functional safety limited by temporal constraints (translated to braking distance). It can be exploited in an early validation approach to help reduce costs of more expensive real world experimentation. It can also determine the boundaries at which sufficient safety can be guaranteed. © 2017 IEEE.
|
|
| 5. |
- Naqvi, Salman Raza, et al.
(författare)
-
Potential of biomass for bioenergy in Pakistan based on present case and future perspectives
- 2018
-
Ingår i: Renewable & sustainable energy reviews. - : Elsevier. - 1364-0321 .- 1879-0690. ; 81:1, s. 1247-1258
-
Forskningsöversikt (refereegranskat)abstract
- Future energy security and environmental issues are major driving forces for increased biomass utilization globally and especially in developing countries like Pakistan. For efficient utilization of indigenous biomass resources in the future energy mix, it is important to gain knowledge of current energy system in various sectors. Some of the technologies and initiatives are under development to achieve transition from non-renewable resources to renewable resources, and reducing fossil fuel dependency and greenhouse gas emissions. Recently, number of proposals has been presented for the development of sustainable biofuels production methods for promise for accelerating a shift away from an unsustainable approach to possible sustainable production practices or a sustainable social, economic and environment. This article presents an extensive literature review of the biomass-based renewable energy potential in Pakistan based on current energy scenario and future perspectives. It also highlights the availability of the indigenous and local biomass resources and potential biomass conversion technologies to convert such resources to bioenergy. The drivers for utilization of indigenous biomass resources in future energy mix and challenges regarding awareness among stakeholders and R & D to fill knowledge gaps are economically restraints. The article concludes with suggestions on future directions and policies for effective implementation of biomass based renewable energy production.
|
|
| 6. |
- Yasin, A., et al.
(författare)
-
Behind the Bait : Delving into PhishTank's hidden data
- 2024
-
Ingår i: Data in Brief. - : Elsevier Inc.. - 2352-3409. ; 52
-
Tidskriftsartikel (refereegranskat)abstract
- Phishing constitutes a form of social engineering that aims to deceive individuals through email communication. Extensive prior research has underscored phishing as one of the most commonly employed attack vectors for infiltrating organizational networks. A prevalent method involves misleading the target by employing phishing URLs concealed through hyperlink strategies. PhishTank, a website employing the concept of crowd-sourcing, aggregates phishing URLs and subsequently verifies their authenticity. In the course of this study, we leveraged a Python script to extract data from the PhishTank website, amassing a comprehensive dataset comprising over 190,0000 phishing URLs. This dataset is a valuable resource that can be harnessed by both researchers and practitioners for enhancing phish- ing filters, fortifying firewalls, security education, and refining training and testing models, among other applications.
|
|
