N-Gram, Semantic-Based Neural Network for Mobile Malware Network Traffic Detection

Mobile malware poses a great challenge to mobile devices and mobile communication. With the explosive growth of mobile networks, it is significant to detect mobile malware for mobile security. Since most mobile malware relies on the networks to coordinate operations, steal information, or launch attacks, evading network monitor is difficult for the mobile malware. In this paper, we present an N-gram, semantic-based neural modeling method to detect the network traffic generated by the mobile malware. In the proposed scheme, we segment the network traffic into flows and extract the application layer payload from each packet. Then, the generated flow payload data are converted into the text form as the input of the proposed model. Each flow text consists of several domains with 20 words. The proposed scheme models the domain representation using convolutional neural network with multiwidth kernels from each domain. Afterward, relationships of domains are adaptively encoded in flow representation using gated recurrent network and then the classification result is obtained from an attention layer. A series of experiments have been conducted to verify the effectiveness of our proposed scheme. In addition, to compare with the state-of-the-art methods, several comparative experiments also are conducted. The experiment results depict that our proposed scheme is better in terms of accuracy.

Download Full-text

LA-GRU: Building Combined Intrusion Detection Model Based on Imbalanced Learning and Gated Recurrent Unit Neural Network

Security and Communication Networks ◽

10.1155/2018/6026878 ◽

2018 ◽

Vol 2018 ◽

pp. 1-13 ◽

Cited By ~ 4

Author(s):

Binghao Yan ◽

Guodong Han

Keyword(s):

Neural Network ◽

Intrusion Detection ◽

False Alarm ◽

False Alarm Rate ◽

Network Traffic ◽

Detection Performance ◽

Imbalanced Learning ◽

Traffic Distribution ◽

Proposed Model ◽

Gated Recurrent Unit

The intrusion detection models (IDMs) based on machine learning play a vital role in the security protection of the network environment, and, by learning the characteristics of the network traffic, these IDMs can divide the network traffic into normal behavior or attack behavior automatically. However, existing IDMs cannot solve the imbalance of traffic distribution, while ignoring the temporal relationship within traffic, which result in the reduction of the detection performance of the IDM and increase the false alarm rate, especially for low-frequency attacks. So, in this paper, we propose a new combined IDM called LA-GRU based on a novel imbalanced learning method and gated recurrent unit (GRU) neural network. In the proposed model, a modified local adaptive synthetic minority oversampling technique (LA-SMOTE) algorithm is provided to handle imbalanced traffic, and then the GRU neural network based on deep learning theory is used to implement the anomaly detection of traffic. The experimental results evaluated on the NSL-KDD dataset confirm that, compared with the existing state-of-the-art IDMs, the proposed model not only obtains excellent overall detection performance with a low false alarm rate but also more effectively solves the learning problem of imbalanced traffic distribution.

Download Full-text

A Deep Convolutional Neural Network for Image Malware Classification

International Journal of Smart Security Technologies ◽

10.4018/ijsst.2019010104 ◽

2019 ◽

Vol 6 (1) ◽

pp. 49-60

Author(s):

Mustapha Belaissaoui ◽

József Jurassec

Keyword(s):

Neural Network ◽

Machine Learning ◽

Convolutional Neural Network ◽

Computer System ◽

System Security ◽

Recurrent Network ◽

Malware Classification ◽

Network Layers ◽

Proposed Model ◽

Neuronal Classification

Malware classification and detection is an important factor in computer system security. However, signature-based methods currently used cannot provide an accurate detection of zero-day attacks and polymorphic viruses. This is why there is a need for detection based on machine learning. The purpose of this work is to present a deep neuronal classification method using convolutional and recurrent network layers in order to obtain the best features for classification. The proposed model achieves 98.73% accuracy on the Microsoft malware dataset.

Download Full-text

Calibrating Network Traffic with One-Dimensional Convolutional Neural Network with Autoencoder and Independent Recurrent Neural Network for Mobile Malware Detection

Security and Communication Networks ◽

10.1155/2021/6695858 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Songjie Wei ◽

Zedong Zhang ◽

Shasha Li ◽

Pengfei Jiang

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Recurrent Neural Network ◽

Network Traffic ◽

Malware Detection ◽

Smart Devices ◽

Detection Accuracy ◽

One Dimensional ◽

Mobile Malware ◽

Mobile Malware Detection

In response to the surging challenge in the number and types of mobile malware targeting smart devices and their sophistication in malicious behavior camouflage, we propose to compose a traffic behavior modeling method based on one-dimensional convolutional neural network with autoencoder and independent recurrent neural network (1DCAE-IndRNN) for mobile malware detection. The design solves the problem that most existing approaches for mobile malware traffic detection struggle with capturing the network traffic dynamics and the sequential characteristics of anomalies in the traffic. We reconstruct and apply the one-dimensional convolutional neural network to extract local features from multiple network flows. The autoencoder is applied to digest the principal traffic features from the neural network and is integrated into the independent recurrent neural network construction to highlight the sequential relationship between the highly significant features. In addition, the Softmax function with the LReLU activation function is adjusted and embedded to the neurons of the independent recurrent neural network to effectively alleviate the problem of unstable training. We conduct a series of experiments to evaluate the effectiveness of the proposed method and its performance for the 1DCAE-IndRNN-integrated detection procedure. The detection results of the public Android malware dataset CICAndMal2017 show that the proposed method achieves up to 98% detection accuracy and recall rates with clear advantages over other benchmark methods.

Download Full-text

Call Details Record Analysis: A Spatiotemporal Exploration toward Mobile Traffic Classification and Optimization

Information ◽

10.3390/info10060192 ◽

2019 ◽

Vol 10 (6) ◽

pp. 192 ◽

Cited By ~ 1

Author(s):

Kashif Sultan ◽

Hazrat Ali ◽

Adeel Ahmad ◽

Zhongshan Zhang

Keyword(s):

Mobile Networks ◽

Network Traffic ◽

Spatiotemporal Analysis ◽

Traffic Classification ◽

Traffic Patterns ◽

Machine Learning Technique ◽

Proposed Model ◽

Learning Technique ◽

Effective Network ◽

Operational Efficacy

The information contained within Call Details records (CDRs) of mobile networks can be used to study the operational efficacy of cellular networks and behavioural pattern of mobile subscribers. In this study, we extract actionable insights from the CDR data and show that there exists a strong spatiotemporal predictability in real network traffic patterns. This knowledge can be leveraged by the mobile operators for effective network planning such as resource management and optimization. Motivated by this, we perform the spatiotemporal analysis of CDR data publicly available from Telecom Italia. Thus, on the basis of spatiotemporal insights, we propose a framework for mobile traffic classification. Experimental results show that the proposed model based on machine learning technique is able to accurately model and classify the network traffic patterns. Furthermore, we demonstrate the application of such insights for resource optimisation.

Download Full-text

Malicious Network Traffic Detection Based on Deep Neural Networks and Association Analysis

Sensors ◽

10.3390/s20051452 ◽

2020 ◽

Vol 20 (5) ◽

pp. 1452 ◽

Cited By ~ 2

Author(s):

Minghui Gao ◽

Li Ma ◽

Heng Liu ◽

Zhijun Zhang ◽

Zhiyan Ning ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Anomaly Detection ◽

Association Analysis ◽

Network Traffic ◽

Deep Neural Network ◽

Deep Neural Networks ◽

Detection System ◽

Detection Systems ◽

Traffic Detection

Anomaly detection systems can accurately identify malicious network traffic, providing network security. With the development of internet technology, network attacks are becoming more and more sourced and complicated, making it difficult for traditional anomaly detection systems to effectively analyze and identify abnormal traffic. At present, deep neural network (DNN) technology achieved great results in terms of anomaly detection, and it can achieve automatic detection. However, there still exists misclassified traffic in the prediction results of deep neural networks, resulting in redundant alarm information. This paper designs a two-level anomaly detection system based on deep neural network and association analysis. We made a comprehensive evaluation of experiments using DNNs and other neural networks based on publicly available datasets. Through the experiments, we chose DNN-4 as an important part of our system, which has high precision and accuracy in identifying malicious traffic. The Apriori algorithm can mine rules between various discretized features and normal labels, which can be used to filter the classified traffic and reduce the false positive rate. Finally, we designed an intrusion detection system based on DNN-4 and association rules. We conducted experiments on the public training set NSL-KDD, which is considered as a modified dataset for the KDDCup 1999. The results show that our detection system has great precision in malicious traffic detection, and it achieves the effect of reducing the number of false alarms.

Download Full-text

Syntax-ignorant N-gram embeddings for dialectal Arabic sentiment analysis

Natural Language Engineering ◽

10.1017/s135132492000008x ◽

2020 ◽

pp. 1-24

Author(s):

Hala Mulki ◽

Hatem Haddad ◽

Mourad Gridach ◽

Ismail Babaoğlu

Keyword(s):

Neural Network ◽

Sentiment Analysis ◽

Deep Neural Network ◽

Syntactic Structure ◽

Network Architectures ◽

Proposed Model ◽

Arabic Dialects ◽

Neural Network Architectures ◽

N Gram ◽

Arabic Sentiment Analysis

Abstract Arabic sentiment analysis models have recently employed compositional paragraph or sentence embedding features to represent the informal Arabic dialectal content. These embeddings are mostly composed via ordered, syntax-aware composition functions and learned within deep neural network architectures. With the differences in the syntactic structure and words’ order among the Arabic dialects, a sentiment analysis system developed for one dialect might not be efficient for the others. Here we present syntax-ignorant, sentiment-specific n-gram embeddings for sentiment analysis of several Arabic dialects. The novelty of the proposed model is illustrated through its features and architecture. In the proposed model, the sentiment is expressed by embeddings, composed via the unordered additive composition function and learned within a shallow neural architecture. To evaluate the generated embeddings, they were compared with the state-of-the art word/paragraph embeddings. This involved investigating their efficiency, as expressive sentiment features, based on the visualisation maps constructed for our n-gram embeddings and word2vec/doc2vec. In addition, using several Eastern/Western Arabic datasets of single-dialect and multi-dialectal contents, the ability of our embeddings to recognise the sentiment was investigated against word/paragraph embeddings-based models. This comparison was performed within both shallow and deep neural network architectures and with two unordered composition functions employed. The results revealed that the introduced syntax-ignorant embeddings could represent single and combinations of different dialects efficiently, as our shallow sentiment analysis model, trained with the proposed n-gram embeddings, could outperform the word2vec/doc2vec models and rival deep neural architectures consuming, remarkably, less training time.

Download Full-text

Nodule Detection with Convolutional Neural Network Using Apache Spark and GPU Frameworks

Applied Sciences ◽

10.3390/app11062838 ◽

2021 ◽

Vol 11 (6) ◽

pp. 2838

Author(s):

Nikitha Johnsirani Venkatesan ◽

Dong Ryeol Shin ◽

Choon Sung Nam

Keyword(s):

Neural Network ◽

Radiation Dose ◽

Convolutional Neural Network ◽

Model Performance ◽

Performance Comparison ◽

Apache Spark ◽

Training Time ◽

Learning Framework ◽

Proposed Model

In the pharmaceutical field, early detection of lung nodules is indispensable for increasing patient survival. We can enhance the quality of the medical images by intensifying the radiation dose. High radiation dose provokes cancer, which forces experts to use limited radiation. Using abrupt radiation generates noise in CT scans. We propose an optimal Convolutional Neural Network model in which Gaussian noise is removed for better classification and increased training accuracy. Experimental demonstration on the LUNA16 dataset of size 160 GB shows that our proposed method exhibit superior results. Classification accuracy, specificity, sensitivity, Precision, Recall, F1 measurement, and area under the ROC curve (AUC) of the model performance are taken as evaluation metrics. We conducted a performance comparison of our proposed model on numerous platforms, like Apache Spark, GPU, and CPU, to depreciate the training time without compromising the accuracy percentage. Our results show that Apache Spark, integrated with a deep learning framework, is suitable for parallel training computation with high accuracy.

Download Full-text

Recurrent neural network-based volumetric fluorescence microscopy

Light Science & Applications ◽

10.1038/s41377-021-00506-9 ◽

2021 ◽

Vol 10 (1) ◽

Author(s):

Luzhe Huang ◽

Hanlong Chen ◽

Yilin Luo ◽

Yair Rivenson ◽

Aydogan Ozcan

Keyword(s):

Neural Network ◽

Image Reconstruction ◽

Fluorescence Microscopy ◽

Recurrent Network ◽

Sample Volume ◽

Depth Of Field ◽

Objective Lens ◽

Wide Field ◽

Volumetric Imaging ◽

3D Image Reconstruction

AbstractVolumetric imaging of samples using fluorescence microscopy plays an important role in various fields including physical, medical and life sciences. Here we report a deep learning-based volumetric image inference framework that uses 2D images that are sparsely captured by a standard wide-field fluorescence microscope at arbitrary axial positions within the sample volume. Through a recurrent convolutional neural network, which we term as Recurrent-MZ, 2D fluorescence information from a few axial planes within the sample is explicitly incorporated to digitally reconstruct the sample volume over an extended depth-of-field. Using experiments on C. elegans and nanobead samples, Recurrent-MZ is demonstrated to significantly increase the depth-of-field of a 63×/1.4NA objective lens, also providing a 30-fold reduction in the number of axial scans required to image the same sample volume. We further illustrated the generalization of this recurrent network for 3D imaging by showing its resilience to varying imaging conditions, including e.g., different sequences of input images, covering various axial permutations and unknown axial positioning errors. We also demonstrated wide-field to confocal cross-modality image transformations using Recurrent-MZ framework and performed 3D image reconstruction of a sample using a few wide-field 2D fluorescence images as input, matching confocal microscopy images of the same sample volume. Recurrent-MZ demonstrates the first application of recurrent neural networks in microscopic image reconstruction and provides a flexible and rapid volumetric imaging framework, overcoming the limitations of current 3D scanning microscopy tools.

Download Full-text

Natural Disasters Intensity Analysis and Classification Based on Multispectral Images Using Multi-Layered Deep Convolutional Neural Network

Sensors ◽

10.3390/s21082648 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2648

Author(s):

Muhammad Aamir ◽

Tariq Ali ◽

Muhammad Irfan ◽

Ahmad Shaf ◽

Muhammad Zeeshan Azam ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Natural Disasters ◽

Deep Convolutional Neural Network ◽

Multispectral Images ◽

Learning Techniques ◽

Proposed Model ◽

Disaster Intensity ◽

And Performance

Natural disasters not only disturb the human ecological system but also destroy the properties and critical infrastructures of human societies and even lead to permanent change in the ecosystem. Disaster can be caused by naturally occurring events such as earthquakes, cyclones, floods, and wildfires. Many deep learning techniques have been applied by various researchers to detect and classify natural disasters to overcome losses in ecosystems, but detection of natural disasters still faces issues due to the complex and imbalanced structures of images. To tackle this problem, we propose a multilayered deep convolutional neural network. The proposed model works in two blocks: Block-I convolutional neural network (B-I CNN), for detection and occurrence of disasters, and Block-II convolutional neural network (B-II CNN), for classification of natural disaster intensity types with different filters and parameters. The model is tested on 4428 natural images and performance is calculated and expressed as different statistical values: sensitivity (SE), 97.54%; specificity (SP), 98.22%; accuracy rate (AR), 99.92%; precision (PRE), 97.79%; and F1-score (F1), 97.97%. The overall accuracy for the whole model is 99.92%, which is competitive and comparable with state-of-the-art algorithms.

Download Full-text