Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Buletin Ilmiah Sarjana Teknik Elektro Control Systems and Optimization Letters
Wani, Sharyar
Unknown Affiliation
Aerospace Engineering Automotive Engineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

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

Found 2 Documents
Search

 1 
AI-Driven Threat Intelligence on Blockchain Using Deep Learning for Decentralized Cyber Risk Prediction Zangana, Hewa Majeed; Beitollahi, Hakem; Muhamad, Sabat Salih; Mohammed, Aquil Mirza; Wani, Sharyar
Control Systems and Optimization Letters Vol 3, No 3 (2025)
Publisher : Peneliti Teknologi Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59247/csol.v3i3.262

Abstract

The increasing complexity of cyber threats such as advanced persistent threats (APTs), ransomware, distributed denial-of-service (DDoS), and smart contract exploits requires cybersecurity solutions that go beyond traditional centralized defenses. This paper proposes an AI-driven threat intelligence framework integrated with blockchain technology for decentralized and trustworthy cyber risk prediction. The novelty of the proposed framework lies in its hybrid architecture, where deep learning–based anomaly detection models (including LSTM and autoencoder networks) analyze real-time cybersecurity data—such as blockchain transaction logs, network activity records, and external threat intelligence feeds—while blockchain is used to securely store, validate, and share AI-generated threat intelligence in a tamper-resistant and decentralized manner. Unlike AI-only solutions that suffer from data integrity and trust issues, or blockchain-only approaches that lack intelligent threat detection, the proposed framework combines the strengths of both technologies to enhance detection accuracy and stakeholder trust. Experimental evaluation conducted in a simulated blockchain environment demonstrates a detection accuracy of 96.4%, a false positive rate of 3.6%, and effective identification of multiple attack categories, including smart contract exploits and 51% attacks. While the framework improves security and transparency for inter-organizational security teams, enterprise networks, and supply-chain partners, it also introduces challenges related to computational overhead and blockchain scalability. Overall, the results indicate that integrating AI-driven threat intelligence with blockchain offers a practical and robust solution for decentralized cybersecurity risk prediction.
A Lightweight Hybrid Template-Matching–CNN Framework with Attention-Guided Fusion for Robust Small Object Detection Zangana, Hewa Majeed; Omar, Marwan; Mirza, Mohammed Aquil; Cao, Xinwei; Wani, Sharyar
Buletin Ilmiah Sarjana Teknik Elektro Vol. 8 No. 1 (2026): February
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v8i1.14751

Abstract

Small object detection in aerial and surveillance imagery remains challenging due to low resolution, occlusion, and background clutter. This study introduces a novel hybrid detection framework that fuses template matching with a deep learning detector (Faster R-CNN) through an attention-guided decision fusion mechanism. The novelty lies in (i) a dual-stage fusion pipeline that integrates precise structural cues from template matching with deep semantic features, and (ii) a custom scale-aware focal loss, adapted from Focal Loss to emphasize hard and small objects by dynamically increasing penalties for low-confidence predictions. Evaluated on a Pascal VOC subset (1000 images, 5 classes), the proposed system achieves an mAP improvement of 3.5% over the Faster R-CNN baseline and surpasses YOLO-Lite and R-CNN variants in precision and recall. The hybrid design adds only a minimal computational overhead (0.45 s/image vs. 0.42 s for Faster R-CNN), demonstrating favorable efficiency–accuracy trade-offs suitable for scalable deployment. These findings highlight the framework’s robustness, particularly in scenes containing occlusion, clutter, or visually small targets. Limitations regarding template dependency are discussed, along with future directions for automatic template generation and real-time video adaptation.
Co-Authors Beitollahi, Hakem Cao, Xinwei Mirza, Mohammed Aquil Mohammed, Aquil Mirza Muhamad, Sabat Salih Omar, Marwan Zangana, Hewa Majeed