Pongoh, Arthur Gregorius
Unknown Affiliation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Systematic Literature Review (SLR): Dampak Pemanfaatan Artificial Intelligence untuk Meningkatkan Cyber Security Pongoh, Arthur Gregorius; Fahreza, Rizqy Achmad; Al Kindi, Bilal; Pribadi, Feddy Setio; Aprilianto, Rizky Ajie
Cyber Security dan Forensik Digital Vol. 7 No. 1 (2024): Edisi Bulan Mei Tahun 2024
Publisher : Fakultas Sains dan Teknologi UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/csecurity.2024.7.1.4486

Abstract

Artificial Intelligence (AI) adalah tambahan kecerdasan pada sistem yang dapat dikelola secara ilmiah dan berkembang di dunia teknologi untuk melayani berbagai aplikasi, termasuk keamanan siber. Kecerdasan buatan memainkan peran penting dalam keamanan siber, memungkinkan deteksi dini ancaman keamanan siber, analisis terperinci terhadap serangan yang muncul, dan respons yang cepat dan akurat. Penelitian ini menggunakan teknik tinjauan literatur sistematis (SLR) untuk menganalisis peran kecerdasan buatan dalam keamanan siber. Pengumpulan data dilakukan dengan mendokumentasikan semua makalah yang memuat temuan penelitian serupa dengan laporan penelitian ini. Makalah yang digunakan dalam penelitian ini adalah 20 makalah dari database ScienceDirect dan Google Scholar. Kecerdasan buatan telah menjadi elemen kunci dalam mendukung upaya untuk melindungi sistem informasi dan jaringan dari ancaman siber yang semakin kompleks. Dengan kemampuannya untuk belajar dari pola-pola data, AI memungkinkan untuk mendeteksi ancaman yang belum pernah terjadi sebelumnya dan memberikan respons secara real-time. Melalui tinjauan literatur sistematis ini, kami menyelidiki berbagai pendekatan dan teknik AI yang telah diterapkan dalam konteks keamanan siber, termasuk penggunaan jaringan syaraf tiruan, algoritma pembelajaran mesin, dan analisis teks. Hasil analisis kami menyoroti bahwa AI telah berhasil digunakan dalam mendeteksi serangan siber, menganalisis pola-pola perilaku yang mencurigakan, dan mengoptimalkan respons keamanan. Implikasi praktis dari penelitian ini adalah pentingnya terus mengembangkan dan mengadopsi solusi AI yang dapat memperkuat pertahanan siber dalam menghadapi ancaman yang terus berkembang.Kata Kunci: Artificial Intelligence, Cyber Security, Systematic Literature Review, Aplikasi Artificial Intelligence -------------------------------------------- Artificial Intelligence (AI) is an augmentation of intelligence within systems that can be managed scientifically and is evolving in the world of technology to serve various applications, including cyber security. Artificial intelligence plays a crucial role in cyber security, enabling early detection of cyber security threats, detailed analysis of emerging attacks, and swift and accurate responses. This research utilizes the systematic literature review (SLR) technique to analyze the role of artificial intelligence in cyber security. Data collection was conducted by documenting all papers containing research findings similar to this research report. The papers used in this study comprise 20 papers from the ScienceDirect and Google Scholar databases.Artificial intelligence has become a key element in supporting efforts to protect information systems and networks from increasingly complex cyber threats. With its ability to learn from data patterns, AI enables the detection of previously unseen threats and provides real-time responses. Through this systematic literature review, we investigated various AI approaches and techniques that have been applied in the context of cyber security, including the use of artificial neural networks, machine learning algorithms, and text analysis. Our analysis highlights that AI has been successfully utilized in detecting cyber attacks, analyzing suspicious behavioral patterns, and optimizing security responses. The practical implications of this research underscore the importance of continually developing and adopting AI solutions that can strengthen cyber defense against evolving threats. Keywords: Artificial Intelligence, Cyber Security, Systematic Literature Review, Application of Artificial Intelligenc
Performance of Deep Face Recognition Models under Adaptive Margin Loss: A Real-Time Evaluation Aditama, Kevin Muhammad Tegar; Nugroho, Anan; Subiyanto, Subiyanto; Pongoh, Arthur Gregorius
International Journal of Artificial Intelligence Research Vol 9, No 1.1 (2025)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v9i1.1.1641

Abstract

Real-time face recognition systems encounter a critical trade-off between high-security demands and computational efficiency, particularly when deployed in unconstrained open-set environments. This study presents a comprehensive benchmarking of four distinct deep learning backbones ResNet100, GhostFaceNet, LAFS, and TransFace specifically trained using the Adaptive Margin Loss (AdaFace) function to handle image quality variations. The primary objective is to identify the optimal architecture for secure attendance systems operating on standard hardware with limited training data. The evaluation protocol employs a rigorous real-world open-set test to quantify performance using False Acceptance Rate (FAR) and False Rejection Rate (FRR). The experimental results demonstrate that ResNet100 establishes the highest security standard, achieving a 0.00% FAR at strict thresholds. Meanwhile, GhostFaceNet emerges as the most balanced solution for resource-constrained deployments, delivering competitive accuracy above 93% with significantly lower computational complexity. Conversely, the Vision Transformer (TransFace) fails to generalize in this low-data regime, resulting in unacceptable false acceptance rates. These findings definitively recommend GhostFaceNet for efficient edge-based implementations, while ResNet100 remains the superior choice for mission-critical security applications.