A Method for TLS Malicious Traffic Identification Based on Machine Learning

2021 ◽  
Vol 105 ◽  
pp. 291-301
Author(s):  
Wei Wang ◽  
Cheng Sheng Sun ◽  
Jia Ning Ye
Keyword(s):  
Feature Extraction ◽  
Relevant Information ◽  
Extraction Process ◽  
Identification Accuracy ◽  
Security And Privacy ◽  
Feature Extraction Method ◽  
Traffic Identification ◽  
Work Related ◽  
Encrypted Traffic ◽  
Network Security Management

With more and more malicious traffic using TLS protocol encryption, efficient identification of TLS malicious traffic has become an increasingly important task in network security management in order to ensure communication security and privacy. Most of the traditional traffic identification methods on TLS malicious encryption only adopt the common characteristics of ordinary traffic, which results in the increase of coupling among features and then the low identification accuracy. In addition, most of the previous work related to malicious traffic identification extracted features directly from the data flow without recording the extraction process, making it difficult for subsequent traceability. Therefore, this paper implements an efficient feature extraction method with structural correlation for TLS malicious encrypted traffic. The traffic feature extraction process is logged in modules, and the index is used to establish relevant information links, so as to analyse the context and facilitate subsequent feature analysis and problem traceability. Finally, Random Forest is used to realize efficient TLS malicious traffic identification with an accuracy of up to 99.38%.

Wavelet-Based Feature Extraction for Behavior Recognition in Mobile Robots

2010 ◽  
Author(s):  
Xin Jin ◽  
Kushal Mukherjee ◽  
Shalabh Gupta ◽  
Asok Ray
Keyword(s):  
Time Series ◽  
Feature Extraction ◽  
Mobile Robots ◽  
Time Series Data ◽  
Piezoelectric Sensor ◽  
Relevant Information ◽  
Series Data ◽  
Test Bed ◽  
Behavior Recognition ◽  
Feature Extraction Method

This paper introduces a dynamic data-driven method for behavior recognition in mobile robots. The core concept of the paper is built upon the principle of symbolic dynamic filtering (SDF) that is used to extract relevant information in complex dynamical systems. The objective here is to identify the robot behavior from time-series data of piezoelectric sensor signals from the pressure sensitive floor in a laboratory environment. A symbolic feature extraction method is presented by partitioning of two-dimensional wavelet images of sensor time-series data. The K-nearest neighbors (k-NN) algorithm is used to identify the patterns extracted by SDF. The proposed method is validated by experimentation on a networked robotics test bed to detect and identify the type and motion profile of mobile robots.

Speaker and Speech Recognition using Deep Neural Network

2018 ◽  
Vol 6 (8) ◽  
pp. 118 ◽  
Author(s):  
Gurpreet Kaur ◽  
Mohit Srivastava ◽  
Amod Kumar
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Feature Extraction ◽  
Speech Recognition ◽  
Deep Neural Network ◽  
Rate Sensitivity ◽  
Extraction Process ◽  
Recall Rate ◽  
Feature Extraction Method ◽  
Work Model

In command and control applications, feature extraction process is very important for good accuracy and less learning time. In order to deal with these metrics, we have proposed an automated combined speaker and speech recognition technique. In this paper five isolated words are recorded with four speakers, two males and two females. We have used the Mel Frequency Cepstral Coefficient (MFCC)  feature extraction method with Genetic Algorithm to optimize the extracted features and generate an appropriate feature set. In first phase, feature extraction using MFCC is executed following the feature optimization using Genetic Algorithm and in last & third phase, training is conducted using the Deep Neural Network. In the end, evaluation and validation of the proposed work model is done by setting real environment. To check the efficiency of the proposed work, we have calculated the parameters like accuracy, precision rate, recall rate, sensitivity and specificity..

scholarly journals Malware Detection Using CNN via Word Embedding in Cloud Computing Infrastructure

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Rong Wang ◽  
Cong Tian ◽  
Lin Yan
Keyword(s):  
Feature Extraction ◽  
Large Scale ◽  
Fog Computing ◽  
Word Embedding ◽  
Security And Privacy ◽  
Experimental Result ◽  
Hierarchical Systems ◽  
Feature Maps ◽  
Feature Extraction Method ◽  
Computing Infrastructure

The Internet of Things (IoT), cloud, and fog computing paradigms provide a powerful large-scale computing infrastructure for a variety of data and computation-intensive applications. These cutting-edge computing infrastructures, however, are nevertheless vulnerable to serious security and privacy risks. One of the most important countermeasures against cybersecurity threats is intrusion detection and prevention systems, which monitor devices, networks, and systems for malicious activity and policy violations. The detection and prevention systems range from antivirus software to hierarchical systems that monitor the traffic of whole backbone networks. At the moment, the primary defensive solutions are based on malware feature extraction. Most known feature extraction algorithms use byte N-gram patterns or binary strings to represent log files or other static information. The information taken from program files is expressed using word embedding (GloVe) and a new feature extraction method proposed in this article. As a result, the relevant vector space model (VSM) will incorporate more information about unknown programs. We utilize convolutional neural network (CNN) to analyze the feature maps represented by word embedding and apply Softmax to fit the probability of a malicious program. Eventually, we consider a program to be malicious if the probability is greater than 0.5; otherwise, it is a benign program. Experimental result shows that our approach achieves a level of accuracy higher than 98%.

scholarly journals Deteksi Aktivitas Mencurigakan Peserta Computer Based Test Menggunakan IP Camera

2019 ◽  
Vol 1 (3) ◽  
pp. 236-243
Author(s):  
Muhammad Ihsan Zul ◽  
Dzaky Kurniawan ◽  
Rahmat Suhatman
Keyword(s):  
Feature Extraction ◽  
Nearest Neighbor ◽  
Extraction Process ◽  
K Nearest Neighbor ◽  
Feature Extraction Method ◽  
Ratio Data ◽  
Ip Camera ◽  
Computer Based ◽  
Illegal Activities ◽  
Pixel Mapping

Common surveillance device that used to monitor an area is known as CCTV. The CCTV will provide results in the form of video recordings, which can then be accessed by wireless communication. In its use, CCTV needs humans to monitor the real condition of the area/place. Then the use of CCTV becomes less efficient when used to oversee a place where the room rarely has movement. Because CCTV cannot detect or identify suspicious actions automatically. This research aim to develop a method that can be used to identify the activity (irregular movements) automatically. In this case, the change to be determined was the activities towards the Politeknik Caltex Riau Computer Based Test (CBT) participants. The CBT room has been employed by the IP Camera to identify participant activities. The IP camera captures the image and the image is then processed by the feature extraction method. Proposed feature exctraction method are background subtraction and pixel mapping. Pixel mapping is a method that maps objects based on specified ratio data. There are 18 ratio data generated by this feature extraction process. The determination of the illegal activities done by using the k-Nearest Neighbor. The Algorithm detects the illegal movement by using 502 datasets, and the accuracy obtained was between 98% - 98.4% with an average accuracy of 98.2% for the value of neighborliness = 3. The result can conclude that the method can identify the illegal activities of a CBT participant in the CBT room

Diabetic Retinopathy Detection Using Optimization Assisted Deep Learning Model: Outlook on Improved Grey Wolf Algorithm

2021 ◽  
pp. 2150035
Author(s):  
Nitin Shivsharan ◽  
Sanjay Ganorkar
Keyword(s):  
Feature Extraction ◽  
Activation Function ◽  
Extraction Process ◽  
Identification Accuracy ◽  
Grey Wolf ◽  
Significant Area ◽  
Major Shortcoming ◽  
Conventional Models ◽  
Two Phases ◽  
Hidden Neurons

In recent days, study on retinal image remains a significant area for analysis. Several retinal diseases are identified by examining the differences occurring in the retina. Anyhow, the major shortcoming between these analyses was that the identification accuracy is not satisfactory. The adopted framework includes two phases namely; (i) feature extraction and (ii) classification. Initially, the input fundus image is subjected to the feature extraction process, where the features like Local Binary Pattern (LBP), Local Vector Pattern (LVP) and Local Tetra Patterns (LTrP) are extracted. These extracted features are subjected to the classification process, where the Deep Belief Network (DBN) is used as the classifier. In addition, to improve the accuracy, the activation function and hidden neurons of DBN are optimally tuned by means of the Self Improved Grey Wolf Optimization (SI-GWO). Finally, the performance of implemented work is compared and proved over the conventional models.

scholarly journals Strategy for Fault Diagnosis on Train Plug Doors Using Audio Sensors

Sensors ◽  
2018 ◽  
Vol 19 (1) ◽  
pp. 3 ◽  
Author(s):  
Yongkui Sun ◽  
Guo Xie ◽  
Yuan Cao ◽  
Tao Wen
Keyword(s):  
Fault Diagnosis ◽  
Extraction Process ◽  
Identification Accuracy ◽  
Permutation Entropy ◽  
Support Vector ◽  
Intrinsic Mode Functions ◽  
Processing Technologies ◽  
Feature Extraction Method ◽  
Multi Scale ◽  
Discrimination Criterion

As the only entry/exit for passengers getting on and off a train, the train plug door is of great importance to keep train operation safe and reliable. As signal processing technologies develop rapidly, taking the easy acquisition advantages of sound signals, a novel fault diagnosis method for train plug doors using multi-scale normalized permutation entropy (MNPE) and an improved particle swarm optimization based multi-class support vector machine (IPSO-MSVM) is proposed. Firstly, sound samples are collected using high-precision audio sensor. In the features extraction process, a hybrid method blending empirical mode decomposition (EMD), multi-scale permutation entropy (MNPE) with Fisher discrimination criterion is utilized. First, EMD is used to decompose each sound signal into several intrinsic mode functions (IMFs) and a residue for stationary processing. Then, MNPE features are extracted from the IMFs. To obtain the most significant features, the Fisher discrimination criterion is further applied. To address the time-consuming defects of traditional grid based method for selecting the optimal parameters of multi-class SVM, an improved PSO (IPSO) is proposed. The superiority of the IPSO-MSVM model and the hybrid feature extraction method was tested on the collected sound samples by comparing to commonly applied methods. Results indicate the identification accuracy of the proposed method is highest, which reaches 90.54%, demonstrating its feasibility.

scholarly journals Metode Wavelet-MFCC dan Korelasi dalam Pengenalan Suara Digit

2020 ◽  
Vol 2 (2) ◽  
pp. 100-108
Author(s):  
Zaurarista Dyarbirru ◽  
Syahroni Hidayat
Keyword(s):  
Feature Extraction ◽  
Speech Recognition ◽  
Recognition System ◽  
Extraction Process ◽  
Extraction Methods ◽  
Transform Method ◽  
Feature Extraction Method ◽  
Average Value ◽  
Advantages And Disadvantages ◽  
Comparison Results

Voice is the sound emitted from living things. With the development of Automatic Speech Recognition (ASR) technology, voice can be used to make it easier for humans to do something. In the ASR extraction process the features have an important role in the recognition process. The feature extraction methods that are commonly applied to ASR are MFCC and Wavelet. Each of them has advantages and disadvantages. Therefore, this study will combine the wavelet feature extraction method and MFCC to maximize the existing advantages. The proposed method is called Wavelet-MFCC. Voice recognition method that does not use recommendations. Determination of system performance using the Word Recoginition Rate (WRR) method which is validated with the K-Fold Cross Validation with the number of folds is 5. The research dataset used is voice recording digits 0-9 in English. The results show that the digit speech recognition system that has been built gives the highest average value of 63% for digit 4 using wavelet daubechies DB3 and wavelet dyadic transform method. As for the comparison results of the wavelet decomposition method used, that the use of dyadic wavelet transformation is better than the wavelet package.

Unsupervised Subspace Extraction via Deep Kernelized Clustering

2021 ◽  
Vol 16 (1) ◽  
pp. 1-15
Author(s):  
Gyoung S. Na ◽  
Hyunju Chang
Keyword(s):  
Feature Extraction ◽  
Side Information ◽  
Feature Space ◽  
Extraction Process ◽  
Extraction Methods ◽  
Feature Extraction Method ◽  
Latent Features ◽  
Benchmark Datasets ◽  
The Given ◽  
Unsupervised Feature Extraction

Feature extraction has been widely studied to find informative latent features and reduce the dimensionality of data. In particular, due to the difficulty in obtaining labeled data, unsupervised feature extraction has received much attention in data mining. However, widely used unsupervised feature extraction methods require side information about data or rigid assumptions on the latent feature space. Furthermore, most feature extraction methods require predefined dimensionality of the latent feature space,which should be manually tuned as a hyperparameter. In this article, we propose a new unsupervised feature extraction method called Unsupervised Subspace Extractor ( USE ), which does not require any side information and rigid assumptions on data. Furthermore, USE can find a subspace generated by a nonlinear combination of the input feature and automatically determine the optimal dimensionality of the subspace for the given nonlinear combination. The feature extraction process of USE is well justified mathematically, and we also empirically demonstrate the effectiveness of USE for several benchmark datasets.

Sign in / Sign up

Export Citation Format

Share Document