Garuda - Garba Rujukan Digital

Phishing Detection in Deep Learning: Systematic Literature Review Abdillah (Scopus ID: 57210600304), Rahmad; Syafitri, Wenni
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 10, No 1 (2024): June 2024
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v10i1.31009

Abstract. Phishing is an attack that is harmful to organizations and individuals in cybersecurity. Many researchers use deep learning techniques to detect phishing. However, the proposed techniques still have shortcomings in terms of performance, especially in detecting unknown attacks, even though they have been developed in such a way. Therefore, to gain a more comprehensive understanding of the current state of research on the use of deep learning to detect phishing, a systematic literature review (SLR) is needed. This SLR aims to identify deep learning techniques, performance measures, overfitting techniques, datasets, parameters, phishing types, and recommendations for future phishing detection research. The method used by SLR consists of a research question and research objective, Search strategy, Inclusion and exclusion criteria, and Data extraction and Analysis. Over the past five years, SLR successfully identified 25 quality articles on phishing detection using deep learning. The contribution of this SLR is to provide insight into the current state of research and identify future research areas of phishing detection using deep learning techniques.

PRO DAN KONTRA PENGGUNAAN AI PADA DUNIA PENDIDIKAN Zamsuri, Ahmad; Syafitri, Wenni; Guntoro, Guntoro; Waldelmi, Idel; Bimby, Novia Putri
Jurnal Pemberdayaan Sosial dan Teknologi Masyarakat Vol 5, No 2 (2025): Desember 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jpstm.v5i2.5414

Abstract: The Community Service (PkM) activity aims to enhance the knowledge of teachers at MI AL FATTAAH regarding the utilization of Generative Artificial Intelligence (Gen-AI) in education. Currently, student assessment is still conducted conventionally, meaning the utilization of Gen-AI technology is not yet optimal. Non-involvement in this technological development could negatively impact the quality of education in the future. Through socialization and education activities, this PkM introduced the concepts, usage, and result analysis of Gen-AI in the educational context, highlighting the pros and cons of its implementation. Effectiveness assessment was conducted using pre-tests and post-tests with the Coefficient of Reproducibility (CR) and Coefficient of Scalability (CS). CR and CS results of 1 indicate that the knowledge transfer was effective and the activity was executed well. This PkM not only improved the teachers' understanding of AI but also has the potential to become a learning model for similar educational institutions. Keywords: Gen-AI, Socialization, Utilization, Education Abstrak: Kegiatan Pengabdian kepada Masyarakat (PkM) ini bertujuan meningkatkan pengetahuan guru MI AL FATTAAH mengenai pemanfaatan Generative Artificial Intelligence (Gen-AI) dalam pendidikan. Selama ini, penilaian murid masih dilakukan secara konvensional, sehingga pemanfaatan teknologi Gen-AI belum optimal. Ketidakterlibatan dalam perkembangan teknologi ini dapat berdampak negatif terhadap kualitas pendidikan di masa depan. Melalui kegiatan sosialisasi dan edukasi, PkM ini memperkenalkan konsep, penggunaan, serta analisis hasil Gen-AI dalam konteks pendidikan, dengan menyoroti aspek pro dan kontra penerapannya. Penilaian efektivitas dilakukan melalui pre-test dan post-test menggunakan koefisien Reprodusibilitas (CR) dan Skalabilitas (CS). Hasil CR dan CS sebesar 1 menunjukkan bahwa transfer pengetahuan berlangsung efektif dan kegiatan terlaksana dengan baik. PkM ini tidak hanya meningkatkan pemahaman guru terhadap AI, tetapi juga berpotensi menjadi model pembelajaran bagi lembaga pendidikan sejenis. Kata kunci: Gen-AI, Sosialisasi, Pemanfaatan, Edukasi

Phishing Detection Model on Social Media Enhanced With CNN and BERT Nurliana Nasution; Wenni Syafitri; Feldiansyah Feldiansyah
Jurnal Testing dan Implementasi Sistem Informasi Vol. 4 No. 1 (2026): Jurnal Testing dan Implementasi Sistem Informasi
Publisher : Lembaga Riset dan Inovasi Almatani

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55583/jtisi.v4i1.2194

Phishing on social media has become an increasingly serious cyber threat because attackers exploit persuasive language, conversational context, and dynamic interaction patterns to deceive users. This study proposes a hybrid CNN-BERT model for detecting phishing content in Indonesian social media text by combining BERT’s contextual semantic representation with CNN’s ability to capture locally relevant textual patterns. The dataset was preprocessed to remove noise, normalize writing variations, and prepare the text for deep learning analysis; class proportions were also examined to support fairer evaluation. Model performance was assessed under multiple data-splitting scenarios and cross-validation to examine robustness and consistency. The experimental results indicate that the proposed hybrid model achieves strong and stable performance across accuracy, precision, recall, and F1-score, and outperforms the baseline model when the BERT backbone is frozen. However, when BERT is fully fine-tuned, the performance gain from the CNN layer becomes marginal, suggesting that strong contextual representations are already highly effective for this task. These findings indicate that integrating CNN and BERT is effective for phishing detection on social media, although domain adaptation challenges, overfitting risk, and real-world deployment constraints remain important considerations. The novelty of this work lies in systematically comparing frozen versus fully fine-tuned IndoBERT backbones with and without a CNN head for Indonesian short-message phishing detection.

PRO DAN KONTRA PENGGUNAAN AI PADA DUNIA PENDIDIKAN Ahmad Zamsuri; Wenni Syafitri; Guntoro Guntoro; Idel Waldelmi; Novia Putri Bimby
Jurnal Pemberdayaan Sosial dan Teknologi Masyarakat Vol. 5 No. 2 (2025): Desember 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jpstm.v5i2.5414

Abstract: The Community Service (PkM) activity aims to enhance the knowledge of teachers at MI AL FATTAAH regarding the utilization of Generative Artificial Intelligence (Gen-AI) in education. Currently, student assessment is still conducted conventionally, meaning the utilization of Gen-AI technology is not yet optimal. Non-involvement in this technological development could negatively impact the quality of education in the future. Through socialization and education activities, this PkM introduced the concepts, usage, and result analysis of Gen-AI in the educational context, highlighting the pros and cons of its implementation. Effectiveness assessment was conducted using pre-tests and post-tests with the Coefficient of Reproducibility (CR) and Coefficient of Scalability (CS). CR and CS results of 1 indicate that the knowledge transfer was effective and the activity was executed well. This PkM not only improved the teachers' understanding of AI but also has the potential to become a learning model for similar educational institutions.Â Â Â Â Â Â Â Â Â Â Â Keywords: Gen-AI, Socialization, Utilization, EducationÂ Â Abstrak: Kegiatan Pengabdian kepada Masyarakat (PkM) ini bertujuan meningkatkan pengetahuan guru MI AL FATTAAH mengenai pemanfaatan Generative Artificial Intelligence (Gen-AI) dalam pendidikan. Selama ini, penilaian murid masih dilakukan secara konvensional, sehingga pemanfaatan teknologi Gen-AI belum optimal. Ketidakterlibatan dalam perkembangan teknologi ini dapat berdampak negatif terhadap kualitas pendidikan di masa depan. Melalui kegiatan sosialisasi dan edukasi, PkM ini memperkenalkan konsep, penggunaan, serta analisis hasil Gen-AI dalam konteks pendidikan, dengan menyoroti aspek pro dan kontra penerapannya. Penilaian efektivitas dilakukan melalui pre-test dan post-test menggunakan koefisien Reprodusibilitas (CR) dan Skalabilitas (CS). Hasil CR dan CS sebesar 1 menunjukkan bahwa transfer pengetahuan berlangsung efektif dan kegiatan terlaksana dengan baik. PkM ini tidak hanya meningkatkan pemahaman guru terhadap AI, tetapi juga berpotensi menjadi model pembelajaran bagi lembaga pendidikan sejenis.Â Kata kunci: Gen-AI, Sosialisasi, Pemanfaatan, Edukasi

Phishing Detection Model on Social Media Enhanced With CNN and BERT Nurliana Nasution; Wenni Syafitri; Feldiansyah Feldiansyah
Jurnal Testing dan Implementasi Sistem Informasi Vol. 4 No. 1 (2026): Jurnal Testing dan Implementasi Sistem Informasi
Publisher : Lembaga Riset dan Inovasi Almatani

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55583/jtisi.v4i1.2194

Phishing on social media has become an increasingly serious cyber threat because attackers exploit persuasive language, conversational context, and dynamic interaction patterns to deceive users. This study proposes a hybrid CNN-BERT model for detecting phishing content in Indonesian social media text by combining BERT’s contextual semantic representation with CNN’s ability to capture locally relevant textual patterns. The dataset was preprocessed to remove noise, normalize writing variations, and prepare the text for deep learning analysis; class proportions were also examined to support fairer evaluation. Model performance was assessed under multiple data-splitting scenarios and cross-validation to examine robustness and consistency. The experimental results indicate that the proposed hybrid model achieves strong and stable performance across accuracy, precision, recall, and F1-score, and outperforms the baseline model when the BERT backbone is frozen. However, when BERT is fully fine-tuned, the performance gain from the CNN layer becomes marginal, suggesting that strong contextual representations are already highly effective for this task. These findings indicate that integrating CNN and BERT is effective for phishing detection on social media, although domain adaptation challenges, overfitting risk, and real-world deployment constraints remain important considerations. The novelty of this work lies in systematically comparing frozen versus fully fine-tuned IndoBERT backbones with and without a CNN head for Indonesian short-message phishing detection.

Deep Learning Driven Ransomware Detection: A Bibliometric Analysis of Research Trends, Knowledge Structure, and Future Directions Guntoro Guntoro; Lisnawita Lisnawita; Loneli Costaner; Wenni Syafitri
Journal of Electrical Engineering and Computer (JEECOM) Vol 8, No 1 (2026)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v8i1.17163

Ransomware has become a major cybersecurity threat because it encrypts data, disrupts services, and evolves rapidly beyond conventional signature-based detection. This study presents a bibliometric analysis of deep learning-driven ransomware detection research, with emphasis on behavioral and dynamic analysis, API-call sequences, system calls, and future research directions. A total of 481 records were retrieved from the Web of Science Core Collection; after screening one retracted publication and two editorial materials, 478 eligible records remained. The eligible corpus was analyzed using Biblioshiny and Bibliometrix. Results show rapid growth from 2022 to 2025, with IEEE Access, Computers & Security, Sensors, Scientific Reports, and International Journal of Information Security among the prominent sources. Keyword and thematic analyses indicate a shift from static detection toward behavior-aware, sequence-based, explainable, and real-time ransomware detection. The findings highlight the need for robust datasets, cross-dataset validation, low-latency inference, explainable deep learning, and integrated detection systems for practical cybersecurity deployment.

The Role Of Big Data Analytics In Strategic Decision-Making And Business Performance: A Systematic Literature Review Amelia Contesa; Ilzi Adrolis; Wenni Syafitri; Abdullah Abdullah
Business System & Innovation Journal Vol. 1 No. 2 (2026): Digital Innovation, Business Resilience, and Organizational Transformation
Publisher : Yayasan Fathurahman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67955/bsij.v1i2.18

Digital transformation has increased organizational reliance on big data analytics (BDA) to support strategic decisions and improve business performance. This study synthesizes evidence on how BDA contributes to strategic decision-making, organizational performance, and innovation through a systematic literature review. The review followed the PRISMA 2020 framework and searched Scopus, IEEE Xplore, ScienceDirect, SpringerLink, and Google Scholar for English-language journal and conference publications from 2021 to 2026. After identification, screening, and full-text eligibility assessment, 33 studies were included and examined using thematic analysis. The findings show that BDA strengthens decision quality and speed by combining analytics capability, predictive modeling, artificial intelligence, and data-driven insights. BDA is also associated with operational efficiency, project success, organizational agility, customer personalization, competitive advantage, sustainability, and innovation capability. The dominant themes were strategic decision-making, business performance, sustainability and innovation, and artificial intelligence with predictive analytics. However, the literature provides limited evidence on explainable and ethical artificial intelligence, human-AI collaboration, real-time analytics, and BDA adoption among small and medium-sized enterprises and organizations in developing economies. The review contributes an integrated view of BDA as a socio-technical and strategic capability and recommends transparent, scalable, and human-centered analytics governance.

Title

Found 17 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 17 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 17 Documents
Search