Change search
Link to record
Permanent link

Direct link
BETA
Shahzad, Raja Khurram
Alternative names
Publications (7 of 7) Show all publications
Hussain, S. A., Fatima, M., Saeed, A., Raza, I. & Shahzad, R. K. (2017). Multilevel classification of security concerns in cloud computing. Applied Computing and Informatics, 13(1), 57-65
Open this publication in new window or tab >>Multilevel classification of security concerns in cloud computing
Show others...
2017 (English)In: Applied Computing and Informatics, ISSN 1578-4487, E-ISSN 2210-8327, Vol. 13, no 1, p. 57-65Article in journal (Refereed) Published
Abstract [en]

Threats jeopardize some basic security requirements in a cloud. These threats generally constitute privacy breach, data leakage and unauthorized data access at different cloud layers. This paper presents a novel multilevel classification model of different security attacks across different cloud services at each layer. It also identifies attack types and risk levels associated with different cloud services at these layers. The risks are ranked as low, medium and high. The intensity of these risk levels depends upon the position of cloud layers. The attacks get more severe for lower layers where infrastructure and platform are involved. The intensity of these risk levels is also associated with security requirements of data encryption, multi-tenancy, data privacy, authentication and authorization for different cloud services. The multilevel classification model leads to the provision of dynamic security contract for each cloud layer that dynamically decides about security requirements for cloud consumer and provider. © 2016 King Saud University

Place, publisher, year, edition, pages
Elsevier B.V., 2017
Keywords
Cloud computing, IaaS, PaaS, SaaS, Security, Virtualization
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-16546 (URN)10.1016/j.aci.2016.03.001 (DOI)2-s2.0-85047871495 (Scopus ID)
Note

open access

Available from: 2018-06-18 Created: 2018-06-18 Last updated: 2018-06-18
Shao, B., Lavesson, N., Boeva, V. & Shahzad, R. K. (2016). A mixture-of-experts approach for gene regulatory network inference. INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS, 14(3), 258-275
Open this publication in new window or tab >>A mixture-of-experts approach for gene regulatory network inference
2016 (English)In: INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS, ISSN 1748-5673, Vol. 14, no 3, p. 258-275Article in journal (Refereed) Published
Abstract [en]

Gene regulatory network (GRN) inference is an important problem in bioinformatics. Many machine learning methods have been applied to increase the inference accuracy. Ensemble learning methods are shown in DREAM3 and DREAM5 challenges to yield a higher inference accuracy than individual algorithms. However, no ensemble method has been proposed to take advantage of the complementarity among existing algorithms from the perspective of network motifs. We propose an ensemble method based on the principle of Mixture-of-Experts ensemble learning. The method can quantitatively evaluate the accuracy of individual algorithms on predicting each type of the network motifs and assign weights to the algorithms accordingly. The individual predictions are then used to generate the ensemble prediction. By performing controlled experiments and statistical tests, the proposed ensemble method is shown to yield a significantly higher accuracy than the generic average ranking method used in the DREAM5 challenge. In addition, a new type of network motif is found in GRN, the inclusion of which can increase the accuracy of the proposed method significantly.

Place, publisher, year, edition, pages
InderScience Publishers, 2016
Keywords
GRN inference; ensemble learning; mixture-of-experts; network motif analysis
National Category
Information Systems Other Computer and Information Science
Identifiers
urn:nbn:se:bth-11852 (URN)10.1504/IJDMB.2016.074876 (DOI)000373392900004 ()
Available from: 2016-05-02 Created: 2016-05-02 Last updated: 2018-01-10Bibliographically approved
Shahzad, R. K., Mehwish, F., Lavesson, N. & Boldt, M. (2015). Consensus decision making in random forests. In: Revised Selected Papers of the First International Workshop on Machine Learning, Optimization, and Big Data: . Paper presented at International Workshop on Machine learning, Optimization and big Data, Taormina, Sicily (pp. 347-358). , 9432
Open this publication in new window or tab >>Consensus decision making in random forests
2015 (English)In: Revised Selected Papers of the First International Workshop on Machine Learning, Optimization, and Big Data, 2015, Vol. 9432, p. 347-358Conference paper, Published paper (Refereed)
Abstract [en]

The applications of Random Forests, an ensemble learner, are investigated in different domains including malware classification. Random Forests uses the majority rule for the outcome, however, a decision from the majority rule faces different challenges such as the decision may not be representative or supported by all trees in Random Forests. To address such problems and increase accuracy in decisions, a consensus decision making (CDM) is suggested. The decision mechanism of Random Forests is replaced with the CDM. The updated Random Forests algorithm is evaluated mainly on malware data sets, and results are compared with unmodified Random Forests. The empirical results suggest that the proposed Random Forests, i.e., with CDM performs better than the original Random Forests.

Series
Machine Learning, Optimization, and Big Data, ISSN 0302-9743 ; 9432
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-12949 (URN)10.1007/978-3-319-27926-8_31 (DOI)
Conference
International Workshop on Machine learning, Optimization and big Data, Taormina, Sicily
Available from: 2016-08-25 Created: 2016-08-25 Last updated: 2018-01-10Bibliographically approved
Shahzad, R. M. (2013). Classification of Potentially Unwanted Programs Using Supervised Learning. (Licentiate dissertation). Karlskrona: Blekinge Institute of Technology
Open this publication in new window or tab >>Classification of Potentially Unwanted Programs Using Supervised Learning
2013 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Malicious software authors have shifted their focus from illegal and clearly malicious software to potentially unwanted programs (PUPs) to earn revenue. PUPs blur the border between legitimate and illegitimate programs and thus fall into a grey zone. Existing anti-virus and anti-spyware software are in many instances unable to detect previously unseen or zero-day attacks and separate PUPs from legitimate software. Many tools also require frequent updates to be effective. By predicting the class of particular piece of software, users can get support before taking the decision to install the software. This Licentiate thesis introduces approaches to distinguish PUP from legitimate software based on the supervised learning of file features represented as n-grams. The overall research method applied in this thesis is experiments. For these experiments, malicious software applications were obtained from anti-malware industrial partners. The legitimate software applications were collected from various online repositories. The general steps of supervised learning, from data preparation (n-gram generation) to evaluation were, followed. Different data representations, such as byte codes and operation codes, with different configurations, such as fixed-size, variable-length, and overlap, were investigated to generate different n-gram sizes. The experimental variables were controlled to measure the correlation between n-gram size, the number of features required for optimal training, and classifier performance. The thesis results suggest that, despite the subtle difference between legitimate software and PUP, this type of software can be classified accurately with a low false positive and false negative rate. The thesis results further suggest an optimal size of operation code-based n-grams for data representation. Finally, the results indicate that classification accuracy can be increased by using a customized ensemble learner that makes use of multiple representations of the data set. The investigated approaches can be implemented as a software tool with a less frequently required update in comparison to existing commercial tools.

Place, publisher, year, edition, pages
Karlskrona: Blekinge Institute of Technology, 2013. p. 154 p.
Series
Blekinge Institute of Technology Licentiate Dissertation Series, ISSN 1650-2140 ; 2
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-00548 (URN)oai:bth.se:forskinfo2408DD58FDB082BDC1257AFC00473485 (Local ID)978-91-7295-247-8 (ISBN)oai:bth.se:forskinfo2408DD58FDB082BDC1257AFC00473485 (Archive number)oai:bth.se:forskinfo2408DD58FDB082BDC1257AFC00473485 (OAI)
Available from: 2013-04-23 Created: 2013-01-23 Last updated: 2018-01-11Bibliographically approved
Shahzad, R. K. & Lavesson, N. (2013). Comparative Analysis of Voting Schemes for Ensemble-based Malware Detection. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications, 4(1), 98-117
Open this publication in new window or tab >>Comparative Analysis of Voting Schemes for Ensemble-based Malware Detection
2013 (English)In: Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications, ISSN 2093-5374, E-ISSN 2093-5382, Vol. 4, no 1, p. 98-117Article in journal (Refereed) Published
Abstract [en]

Malicious software (malware) represents a threat to the security and the privacy of computer users. Traditional signature-based and heuristic-based methods are inadequate for detecting some forms of malware. This paper presents a malware detection method based on supervised learning. The main contributions of the paper are two ensemble learning algorithms, two pre-processing techniques, and an empirical evaluation of the proposed algorithms. Sequences of operational codes are extracted as features from malware and benign files. These sequences are used to create three different data sets with different configurations. A set of learning algorithms is evaluated on the data sets. The predictions from the learning algorithms are combined by an ensemble algorithm. The predicted outcome of the ensemble algorithm is decided on the basis of voting. The experimental results show that the veto approach can accurately detect both novel and known malware instances with the higher recall in comparison to majority voting, however, the precision of the veto voting is lower than the majority voting. The veto voting is further extended as trust-based veto voting. A comparison of the majority voting, the veto voting, and the trust-based veto voting is performed. The experimental results indicate the suitability of each voting scheme for detecting a particular class of software. The experimental results for the composite F1-measure indicate that the majority voting is slightly better than the trusted veto voting while the trusted veto is significantly better than the veto classifier.

Place, publisher, year, edition, pages
Innovative Information Science & Technology Research Group, 2013
Keywords
Malware detection, scareware, veto voting, feature extraction, classification, majority voting, ensemble, trust, malicious software
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-7001 (URN)oai:bth.se:forskinfo026B75A577C2FBD6C1257B3400281F31 (Local ID)oai:bth.se:forskinfo026B75A577C2FBD6C1257B3400281F31 (Archive number)oai:bth.se:forskinfo026B75A577C2FBD6C1257B3400281F31 (OAI)
External cooperation:
Note

Open Access Journal

Available from: 2013-03-20 Created: 2013-03-20 Last updated: 2018-01-11Bibliographically approved
Shahid, M. & Shahzad, R. M. (2013). Selection of a Graduate Thesis Topic in a Multicultural Educational Environment. In: : . Paper presented at Lärarlärdom Högskolepedagogisk konferens. Kristianstad: Kristianstad University Press
Open this publication in new window or tab >>Selection of a Graduate Thesis Topic in a Multicultural Educational Environment
2013 (English)Conference paper, Published paper (Refereed)
Abstract [en]

This article presents a case study, performed at Blekinge Institute of Technology (BTH), Sweden, about the topic selection routines for a graduate thesis. The study focuses on the international graduate students who are having different academic cultures of their respective countries. Given that BTH has succeeded in the provision of an academic environment that has been efficient in absorbing different academic cultures in a productive manner at a reasonably good scale. However, in a multi-cultural educational environment, it is a challenge for most international students to adapt to the new academic culture and select the graduate thesis topic according to their real potential. Our findings gathered through an online survey, questionnaire, and focus group discussion is presented. The conclusions indicate, albeit, BTH has well defined routines for the thesis selection, the international graduate students face problems at the stage of thesis selection. The article concludes with suggestions to refine the thesis selection process at the micro level to help both students and staff.

Place, publisher, year, edition, pages
Kristianstad: Kristianstad University Press, 2013
National Category
Pedagogy
Identifiers
urn:nbn:se:bth-6400 (URN)oai:bth.se:forskinfoECD360DE6F378EBAC1257DFE0045AFE6 (Local ID)oai:bth.se:forskinfoECD360DE6F378EBAC1257DFE0045AFE6 (Archive number)oai:bth.se:forskinfoECD360DE6F378EBAC1257DFE0045AFE6 (OAI)
External cooperation:
Conference
Lärarlärdom Högskolepedagogisk konferens
Note

Higher Education Pedagogy Conference

Available from: 2015-03-05 Created: 2015-03-04 Last updated: 2016-09-09Bibliographically approved
Shahzad, R. K. & Lavesson, N. (2012). Veto-based Malware Detection. In: : . Paper presented at Seventh International Conference on Availability, Reliability and Security. Prague: IEEE Computer Society
Open this publication in new window or tab >>Veto-based Malware Detection
2012 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Malicious software (malware) represents a threat to the security and privacy of computer users. Traditional signature-based and heuristic-based methods are unsuccessful in detecting some forms of malware. This paper presents a malware detection approach based on supervised learning. The main contributions of the paper are an ensemble learning algorithm, two pre-processing techniques, and an empirical evaluation of the proposed algorithm. Sequences of operational codes are extracted as features from malware and benign files. These sequences are used to produce three different data sets with different configurations. A set of learning algorithms is evaluated on the data sets and the predictions are combined by the ensemble algorithm. The predicted output is decided on the basis of veto voting. The experimental results show that the approach can accurately detect both novel and known malware instances with higher recall in comparison to majority voting.

Place, publisher, year, edition, pages
Prague: IEEE Computer Society, 2012
Keywords
Malware, scareware, detection, veto voting, feature extraction, classification, majority voting, ensembles
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-7087 (URN)10.1109/ARES.2012.85 (DOI)oai:bth.se:forskinfoA439EF0C7155840AC1257AD000521D72 (Local ID)oai:bth.se:forskinfoA439EF0C7155840AC1257AD000521D72 (Archive number)oai:bth.se:forskinfoA439EF0C7155840AC1257AD000521D72 (OAI)
Conference
Seventh International Conference on Availability, Reliability and Security
Available from: 2012-12-12 Created: 2012-12-10 Last updated: 2018-01-11Bibliographically approved
Organisations

Search in DiVA

Show all publications