Telkom University

About: Telkom University is a education organization based out in Bandung, Indonesia. It is known for research contribution in the topics: Computer science & Social media. The organization has 8300 authors who have published 8184 publications receiving 18234 citations.

Preliminary Investigation

Abstract: Secure engineering is relatively more popular for software development methodologies which use standard SDLC such as waterfall, prototyping, etc. However, for agile methodologies (such as extreme programming, scrum, etc.), the adoption of secure engineering is still a debate among academics and practitioners since it potentially alter the nature of agile. This paper tries to investigate farthest works of the adaptation of secure engineering to agile methods, and to compile best propositions on how to conduct agile software development by still adhering security principles. From the review, addition/recruitment of security engineer into team is the most appreciated, while the modification of agile methodology and project management is not really favored by practitioners. This paper will be a starting point of further study to fill research/knowledge gap which is provided in this paper.

Improving AdaBoost-based Intrusion Detection System (IDS) Performance on CIC IDS 2017 Dataset

Abstract: This paper considers the use of Synthetic Minority Oversampling Technique (SMOTE), Principal Component Analysis (PCA), and Ensemble Feature Selection (EFS) to improve the performance of AdaBoost-based Intrusion Detection System (IDS) on the latest and challenging CIC IDS 2017 Dataset [1]. Previous research [1] has proposed the use of AdaBoost classifier to cope with the new dataset. However, due to several problems such as imbalance of training data and inappropriate selection of classification methods, the performance is still inferior. In this research, we aim at constructing an improvement performance intrusion detection approach to handle the imbalance of training data, SMOTE is selected to tackle the problem. Moreover, Principal Component Analysis (PCA) and Ensemble Feature Selection (EFS) are applied as the feature selection to select important attributes from the new dataset. The evaluation results show that the proposed AdaBoost classifier using PCA and SMOTE yields Area Under the Receiver Operating Characteristic curve (AUROC) of 92% and the AdaBoost classifier using EFS and SMOTE produces an accuracy, precision, recall, and F1 Score of 81.83 %, 81.83%, 100%, and 90.01% respectively.