Deep learning Archives - Program Studi S1 Informatika

Enhancing Phishing Detection: A Novel Hybrid Deep Learning Framework for Cybercrime Forensics

February 5, 2024/in Publikasi /by Program Studi Informatika

Enhancing Phishing Detection: A Novel Hybrid Deep Learning Framework for Cybercrime Forensics

Protecting against interference is essential at a time when wireless communications are essential for sending large amounts of data. Our research presents a novel deep learning technique, the ResNeXt method and embedded Gated Recurrent Unit (GRU) model (RNT), rigorously developed for real-time phishing attack detection. Focused on countering the escalating threat of phishing assaults and bolstering digital forensics, our systematic approach involves SMOTE for managing data imbalance during initial data processing. The model’s discriminative capability is improved, particularly in the feature extraction process, when autoencoders and ResNet (EARN) are integrated with feature engineering. The ensemble technique of feature extraction reveals crucial data patterns. At the core of our AI categorization is the RNT model, optimized using hyperparameters through the Jaya optimization method (RNT-J). Rigorously tested on real phishing attack datasets, our AI model consistently outperforms state-of-the-art algorithms by a substantial margin of 11% to 19% while maintaining exceptional computing efficiency. Furthermore, our model achieves 98% accuracy, low false positive/false negative values, and a statistical execution time with a mean of 36.99s, median of 35.99s, minimum of 34.99s, maximum of 41.99s, and a standard deviation of 1.10s. Moreover, it demonstrates superior accuracy with SMOTE (98%) and without SMOTE (83%) compared to other algorithms. This state-of-the-art AI study, which focuses on digital forensics, offers enhanced security and optimized productivity for businesses and industries, signifying a breakthrough in the continuing battle against phishing attempts. Through strengthening protection against interference in wireless communication, our AI research strives to amplify data accessibility, resilience, and trustworthiness in the face of cybersecurity threats within the organizational context.

Source : pdf

Klasifikasi URL Berbahaya yang Efisien: MBERT – Varian BERT yang Dimodifikasi untuk Peningkatan Pemahaman Semantik

January 29, 2024/in Khazanah, Publikasi /by Program Studi Informatika

Klasifikasi URL Berbahaya yang Efisien: MBERT – Varian BERT yang Dimodifikasi untuk Peningkatan Pemahaman Semantik

Boyang Yu1, Fei Tang1, Daji Ergu1, Rui Zeng2, Bo Ma1, and Fangyao Liu1

1College of Electronic and Information, Southwest Minzu University, Chengdu, China
2College of Pharmacy, Southwest Minzu University, Chengdu, China

Corresponding author: Fangyao Liu (FLIU028@163.COM)

Situs web berbahaya menghadirkan ancaman besar terhadap keamanan dan privasi individu yang menggunakannya
internet. Pendekatan tradisional untuk mengidentifikasi situs-situs berbahaya ini sulit untuk diseimbangkan
strategi serangan yang berkembang. Dalam beberapa tahun terakhir, model bahasa telah muncul sebagai solusi potensial
secara efektif mendeteksi dan mengkategorikan situs web berbahaya. Penelitian ini memperkenalkan novel BiDirectional
Model Representasi Encoder dari Transformers (BERT), berdasarkan arsitektur encoder Transformer,
dirancang untuk menangkap karakteristik terkait dari alamat web berbahaya. Selain itu, bahasa berskala besar
model digunakan untuk pelatihan, penilaian kumpulan data, dan analisis interpretabilitas. Hasil evaluasi
menunjukkan efektivitas model bahasa besar dalam mengklasifikasikan situs web berbahaya secara akurat,
mencapai tingkat presisi yang mengesankan sebesar 94,42%. Performa ini melampaui bahasa yang ada
model. Selain itu, analisis interpretabilitas menyoroti proses pengambilan keputusan model,
meningkatkan pemahaman kita tentang hasil klasifikasinya. Kesimpulannya, model BERT yang diusulkan, dibangun
pada arsitektur encoder Transformer, menunjukkan kinerja yang kuat dan kemampuan interpretasi dalam identifikasi
dari situs web berbahaya. Ini menjanjikan sebagai solusi untuk meningkatkan keamanan pengguna jaringan dan melakukan mitigasi risiko yang terkait dengan aktivitas online berbahaya.

source: IEEE

Botnet detection based on network flow summary and deep learning

January 14, 2023/in Publikasi /by Informatika

Botnet detection based on network flow summary and deep learning

by Abdurrahman Pektaş, Tankut Acarman

International Journal of Network Management

A botnet is a group of compromised Internet-connected devices controlled remotely by cyber criminals to launch coordinated attacks and to perform various malicious activities. Since botnets continuously adapt themselves to the evolving countermeasures introduced by both network and host-based detection mechanism, the traditional approaches do not provide adequate protection to botnet threat. On the one hand, behavioral analysis of network traffic can play a key role to detect botnets. For instance, behavioral analysis can be applied to observe and discover communication patterns that botnets operate during their life cycle. On the other hand, deep learning has been successfully applied to various classification tasks, and it is also a promising solution for botnet discovery. In this paper, we apply deep neural network to detect botnet by modeling network traffic flow. The performance of the proposed method is evaluated with publicly available large-scale communication traces. The experimental results illustrate that deep learning is an efficient and effective method for identifying botnet traffic with a high true positive rate (attack detection rate) and low false positive alarm rate.

Graph convolutional network for fMRI analysis based on connectivity neighborhood

January 7, 2023/in Publikasi /by Informatika

Graph convolutional network for fMRI analysis based on connectivity neighborhood

by Lebo Wang, Kaiming Li, Xiaoping P. Hu

MIT Press – Journals

There have been successful applications of deep learning to functional magnetic resonance imaging (fMRI), where fMRI data were mostly considered to be structured grids, and spatial features from Euclidean neighbors were usually extracted by the convolutional neural networks (CNNs) in the computer vision field. Recently, CNN has been extended to graph data and demonstrated superior performance. Here, we define graphs based on functional connectivity and present a connectivity-based graph convolutional network (cGCN) architecture for fMRI analysis. Such an approach allows us to extract spatial features from connectomic neighborhoods rather than from Euclidean ones, consistent with the functional organization of the brain. To evaluate the performance of cGCN, we applied it to two scenarios with resting-state fMRI data. One is individual identification of healthy participants and the other is classification of autistic patients from normal controls. Our results indicate that cGCN can effectively capture functional connectivity features in fMRI analysis for relevant applications.

Convolutional neural networks: an overview and application in radiology

January 5, 2023/in Publikasi /by Program Studi Informatika

Convolutional neural networks: an overview and application in radiology

by R Yamashita, M Nishio, RKG Do, K Togashi

Insights into imaging

Convolutional neural network (CNN), a class of artificial neural networks that has become dominant in various computer vision tasks, is attracting interest across a variety of domains, including radiology. CNN is designed to automatically and adaptively learn spatial hierarchies of features through backpropagation by using multiple building blocks, such as convolution layers, pooling layers, and fully connected layers. This review article offers a perspective on the basic concepts of CNN and its application to various radiological tasks, and discusses its challenges and future directions in the field of radiology. Two challenges in applying CNN to radiological tasks, small dataset and overfitting, will also be covered in this article, as well as techniques to minimize them. Being familiar with the concepts and advantages, as well as limitations, of CNN is essential to leverage its potential in diagnostic radiology, with the goal of augmenting the performance of radiologists and improving patient care.

Key Points

• Convolutional neural network is a class of deep learning methods which has become dominant in various computer vision tasks and is attracting interest across a variety of domains, including radiology.

• Convolutional neural network is composed of multiple building blocks, such as convolution layers, pooling layers, and fully connected layers, and is designed to automatically and adaptively learn spatial hierarchies of features through a backpropagation algorithm.

• Familiarity with the concepts and advantages, as well as limitations, of convolutional neural network is essential to leverage its potential to improve radiologist performance and, eventually, patient care.

A comprehensive survey on graph neural networks

January 5, 2023/in Publikasi /by Program Studi Informatika

A comprehensive survey on graph neural networks

by Zonghan Wu; Shirui Pan; Fengwen Chen; Guodong Long; Chengqi Zhang

IEEE Transactions on Neural Networks and Learning Systems

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications, where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial-temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.

Posts

Program Studi Informatika

Informasi Tentang