Widyawan

Widyawan

Auto-generated profile, based on publicly available information

Widyawan

Department of Electrical Engineering and Information Technology, Universitas Gadjah Mada, Yogyakarta, Indonesia

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 March 2024 in IEEE Access
Verified
Journal Article
Open access
RYRajif Agung Yunmar
Rajif Agung Yunmar
SKSri Suning Kusumawardani
Sri Suning Kusumawardani
WIWidyawan
Widyawan
FMFadi Mohsen
Fadi Mohsen
Over the last decade, numerous research efforts have been dedicated to countering malicious mobile applications. Given its market share, Android OS has been the primary target for most of these apps. Researchers have devised numerous solutions to protect Android devices and their users, categorizing them into static and dynamic approaches. Each of these approaches has its own advantages and disadvantages. The hybrid approach aims to combine the benefits of both. This study closely examines the hybrid solutions proposed between 2012 and 2023, highlighting their strengths and limitations. The objective of this study is to provide a comprehensive review of existing research on Android malware detection using a hybrid approach. Our review identifies several issues related to hybrid detection approaches, including datasets, feature utilization and selection, working environments, detection order mechanisms, integrity of the detection step, detection algorithms, and the use of automated input generation. Key findings of this study include: (i) the majority of studies have not adequately addressed on-device detection and have overlooked the importance of system usability, (ii) many studies rely on outdated datasets that do not accurately represent the current threat landscape, (iii) there is a need for a methodology to detect zero-day attacks, and (iv) most research has not paid attention to the impact of automated input generation on malware behavior and code coverage. We also discuss some open issues and future directions on the aspect that will help to substantiate the hybrid approach study.

6 May 2024 in Data in Brief
Verified
Journal Article
Open access
SSSyaifuddin Saif
Syaifuddin Saif
WWWidyawan Widyawan
Widyawan Widyawan
RFRidi Ferdiana
Ridi Ferdiana
The proliferation of Internet of Things devices has ushered in a new era of connectivity and con-venience, yet it has also exposed a myriad of security challenges, with Distributed Denial of Service attacks posing a significant threat. This paper introduces the IoT-DH dataset, a novel and extensive dataset designed for the purpose of classifying, identifying, and detecting DDoS attacks within IoT ecosystems. The dataset encompasses diverse scenarios and network configurations, providing a realistic representation of IoT environments. We present a systematic analysis of the IoT-DH dataset, exploring its features and characteristics that mirror the complexities of real-world IoT net-works. The dataset includes a variety of attack scenarios, incorporating different attack vectors and intensities to capture the evolving nature of DDoS threats in IoT. Our approach facilitates the development and evaluation of robust machine learning and deep learning models for effective DDoS attack mitigation. Furthermore, we propose a multi-faceted methodology for leveraging the IoT-DH dataset, encompassing classification techniques to categorize attack types, identification mechanisms to pinpoint malicious entities, and detection algorithms to promptly respond to ongoing DDoS incidents. The efficacy of these methodologies is demonstrated through extensive experiments and evaluations, showcasing their ability to enhance the security posture of IoT environments.

6 February 2025 in Results in Engineering
Verified
Journal Article
Open access
MPMichael Stephen Moses Pakpahan
Michael Stephen Moses Pakpahan
LNLukito Edi Nugroho
Lukito Edi Nugroho
WIWidyawan
Widyawan

18 March 2025 in IEEE Access
Verified
Journal Article
Open access
DTDedi Triyanto
Dedi Triyanto
IMI Wayan Mustika
I Wayan Mustika
WIWidyawan
Widyawan
PPPraphan Pavarangkoon
Praphan Pavarangkoon
Mobile edge computing (MEC) improves network performance by minimizing latency and assigning computing tasks to edge servers. Nonetheless, delegating calculations in environments with elevated device density poses considerable difficulties. Ensuring equity in resource distribution among users is essential for preserving network stability and user satisfaction in these contexts. This research formulates the Fairness-aware Computation Offloading Optimization (FACOO) algorithm. The Lyapunov approach and sequential least squares quadratic programming (SLSQP) are used to ascertain the best offloading ratio, transmission power, and CPU frequency while complying with signal-to-interference-plus-noise ratio (SINR) limitations. Energy harvesting (EH) is built into FACOO to prolong the battery life of the device and to ensure that MEC systems, which are limited in resources, are more sustainable. The results show that FACOO greatly improves throughput and fairness while using much less energy, especially in settings where a lot of nodes are spread out over a large area. Comprehensive simulations show that the method effectively balances fairness, throughput, and energy use, making it a workable way to improve resource allocation in MEC systems.

7 August 2024 in JURNAL SISTEM INFORMASI BISNIS
Verified
Journal Article
Open access
PDF file
WWWidyawan Widyawan
Widyawan Widyawan
BUBayu Prasetiyo Utomo
Bayu Prasetiyo Utomo
MRMuhammad Nur Rizala
Muhammad Nur Rizala
One of the important implementations in machine learning is Named Entity Recognition (NER), which is used to process text and extract entities such as people, organizations, laws, religions, and locations. NER for the Indonesian language still faces significant challenges due to the lack of high-quality labelled datasets, which limits the development of more advanced models. To address this issue, we utilized several pre-trained BERT models (bert-base-uncased, indobenchmark/indobert-base-p1, indolem/indobert-base-uncased) and datasets (NERGRIT-IndoNLU, NERGRIT-Corpus, NERUGM, and NERUI). This study proposes a novel fusion approach by integrating deep learning architectures such as CNN, Bi-LSTM, Bi-GRU, and CRF to detect 19 entities. This approach enhances BERT’s sequence modelling and feature extraction capabilities, while CRF improves entity prediction by enforcing global word-sequence constraints. Experimental results demonstrate that the fusion approach outperforms previous methods. On the bert-base-uncased dataset, accuracy reached 94.75%, while indobenchmark/indobert-base-p1 achieved 95.75%, and indolem/indobert-base-uncased achieved 95.85%. This study emphasizes the effectiveness of combining deep learning architectures with pre-trained transformers to improve NER performance in the Indonesian language. The proposed methodology offers significant advancements in entity extraction for languages with limited datasets, such as Indonesian.