scholarly journals Face Spoofing Detection using Mixed Feature with Deep Convolutional Neural Networks

2020 ◽  
Vol 8 (5) ◽  
pp. 3309-3314
Keyword(s):  
Deep Learning ◽  
Detection System ◽  
Attack Detection ◽  
Detection Methods ◽  
Deep Convolutional Neural Networks ◽  
Replay Attack ◽  
Multiple Features ◽  
Spoofing Detection ◽  
Occurrence Matrix ◽  
Face Spoofing

Nowadays, face biometric-based access control systems are becoming ubiquitous in daily life while they are still vulnerable to spoofing attacks. Developing robust and reliable methods to prevent such frauds is unavoidable. As deep learning techniques have achieved satisfactory performances in computer vision, they have also been applied to face spoofing detection. However, the numerous parameters in these deep learning-based detection methods cannot be updated to optimum due to limited data. In this paper,a highly accurate face spoof detection system using multiple features and deep learning is proposed. The input video is broken into frames using content-based frame extraction. From each frame, the face of the person is cropped.From the cropped images multiple features like Histogram of Gradients (HoG), Local Binary Pattern (LBP), Center Symmetric LBP (CSLBP), and Gray level co-occurrence Matrix (GLCM) are extracted to train the Convolutional Neural Network(CNN). Training and testing are performed separately by using collected sample data.Experiments on the standard spoof database called Replay-Attack database the proposed system outperform other state-of-the-art techniques, presenting great results in terms of attack detection.

scholarly journals IoT Cloud-Based Framework for Face Spoofing Detection with Deep Multicolor Feature Learning Model

2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Sajad Einy ◽  
Cemil Oz ◽  
Yahya Dorostkar Navaei
Keyword(s):  
Deep Learning ◽  
Computer Security ◽  
Feature Learning ◽  
Face Image ◽  
Public Access ◽  
Training Data ◽  
Learning Approach ◽  
Replay Attack ◽  
Spoofing Detection ◽  
Face Spoofing

A face-based authentication system has become an important topic in various fields of IoT applications such as identity validation for social care, crime detection, ATM access, computer security, etc. However, these authentication systems are vulnerable to different attacks. Presentation attacks have become a clear threat for facial biometric-based authentication and security applications. To address this issue, we proposed a deep learning approach for face spoofing detection systems in IoT cloud-based environment. The deep learning approach extracted features from multicolor space to obtain more information from the input face image regarding luminance and chrominance data. These features are combined and selected by the Minimum Redundancy Maximum Relevance (mRMR) algorithm to provide an efficient and discriminate feature set. Finally, the extracted deep color-based features of the face image are used for face spoofing detection in a cloud environment. The proposed method achieves stable results with less training data compared to conventional deep learning methods. This advantage of the proposed approach reduces the time of processing in the training phase and optimizes resource management in storing training data on the cloud. The proposed system was tested and evaluated based on two challenging public access face spoofing databases, namely, Replay-Attack and ROSE-Youtu. The experimental results based on these databases showed that the proposed method achieved satisfactory results compared to the state-of-the-art methods based on an equal error rate (EER) of 0.2% and 3.8%, respectively, for the Replay-Attack and ROSE-Youtu databases.

Application of Deep Learning Technique in an Intrusion Detection System

2020 ◽  
Vol 19 (02) ◽  
pp. 2050016
Author(s):  
Shideh Saraeian ◽  
Mahya Mohammadi Golchi
Keyword(s):  
Deep Learning ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Visual Analysis ◽  
Detection System ◽  
Denial Of Service ◽  
Attack Detection ◽  
Hybrid Network ◽  
Machine Learning Techniques ◽  
Learning Technique

Comprehensive development of computer networks causes the increment of Distributed Denial of Service (DDoS) attacks. These types of attacks can easily restrict communication and computing. Among all the previous researches, the accuracy of the attack detection has not been properly addressed. In this study, deep learning technique is used in a hybrid network-based Intrusion Detection System (IDS) to detect intrusion on network. The performance of the proposed technique is evaluated on the NSL-KDD and ISCXIDS 2012 datasets. We performed traffic visual analysis using Wireshark tool and did some experimentations to prove the superiority of the proposed method. The results have shown that our proposed method achieved higher accuracy in comparison with other useful machine learning techniques.

scholarly journals Toward Developing Efficient Conv-AE-Based Intrusion Detection System Using Heterogeneous Dataset

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1771
Author(s):  
Muhammad Ashfaq Khan ◽  
Juntae Kim
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Performance Metrics ◽  
Detection System ◽  
Rapid Development ◽  
Research Problem ◽  
Vital Role ◽  
Attack Detection ◽  
Detection Methods ◽  
Malicious Attacks

Recently, due to the rapid development and remarkable result of deep learning (DL) and machine learning (ML) approaches in various domains for several long-standing artificial intelligence (AI) tasks, there has an extreme interest in applying toward network security too. Nowadays, in the information communication technology (ICT) era, the intrusion detection (ID) system has the great potential to be the frontier of security against cyberattacks and plays a vital role in achieving network infrastructure and resources. Conventional ID systems are not strong enough to detect advanced malicious threats. Heterogeneity is one of the important features of big data. Thus, designing an efficient ID system using a heterogeneous dataset is a massive research problem. There are several ID datasets openly existing for more research by the cybersecurity researcher community. However, no existing research has shown a detailed performance evaluation of several ML methods on various publicly available ID datasets. Due to the dynamic nature of malicious attacks with continuously changing attack detection methods, ID datasets are available publicly and are updated systematically. In this research, spark MLlib (machine learning library)-based robust classical ML classifiers for anomaly detection and state of the art DL, such as the convolutional-auto encoder (Conv-AE) for misuse attack, is used to develop an efficient and intelligent ID system to detect and classify unpredictable malicious attacks. To measure the effectiveness of our proposed ID system, we have used several important performance metrics, such as FAR, DR, and accuracy, while experiments are conducted on the publicly existing dataset, specifically the contemporary heterogeneous CSE-CIC-IDS2018 dataset.

scholarly journals DoS and DDoS Attack Detection Using Deep Learning and IDS

2020 ◽  
Vol 17 (4A) ◽  
pp. 655-661
Author(s):  
Mohammad Shurman ◽  
Rami Khrais ◽  
Abdulrahman Yateem
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Detection System ◽  
Denial Of Service ◽  
Attack Detection ◽  
Target System ◽  
Online Systems ◽  
Ddos Attack ◽  
Long Short Term Memory ◽  
Ddos Attack Detection

In the recent years, Denial-of-Service (DoS) or Distributed Denial-of-Service (DDoS) attack has spread greatly and attackers make online systems unavailable to legitimate users by sending huge number of packets to the target system. In this paper, we proposed two methodologies to detect Distributed Reflection Denial of Service (DrDoS) attacks in IoT. The first methodology uses hybrid Intrusion Detection System (IDS) to detect IoT-DoS attack. The second methodology uses deep learning models, based on Long Short-Term Memory (LSTM) trained with latest dataset for such kinds of DrDoS. Our experimental results demonstrate that using the proposed methodologies can detect bad behaviour making the IoT network safe of Dos and DDoS attacks

scholarly journals Detection of Face Spoofing using Color Texture and Edge Features

2020 ◽  
Vol 8 (5S) ◽  
pp. 33-37
Keyword(s):  
Recognition System ◽  
Replay Attack ◽  
Authorized User ◽  
Detection Techniques ◽  
Detection Approach ◽  
Spoofing Detection ◽  
Wide Scale ◽  
Edge Features ◽  
Face Spoofing ◽  
Color Texture

The wide scale use of facial recognition systems has caused concerns about spoofing attacks. Security is essential requirement for a face recognition system to provide reliable protection against spoofing attacks. Spoofing happens in situations where someone tries to behave as an authorized user to obtain illicitly access the protected system to gain advantage over it. In order to identify spoofing attacks, face spoofing detection approaches have been used. Traditional face spoofing detection techniques are not good enough as most of them focus only on the gray scale information and discarding the color information. Here a face spoofing detection approach with color texture and edge analysis is presented. The approach for investigating the texture of input images, Local binary pattern and Edge Histogram descriptor are proposed. Experiments on a publicly available dataset, Replay attack, showed excellent results compared to existing works.

scholarly journals Deep Learning Based Attack Detection in IIoT using Two-Level Intrusion Detection System

2021 ◽  
Author(s):  
Kathiroli Raja ◽  
Krithika Karthikeyan ◽  
Abilash B ◽  
Kapal Dev ◽  
Gunasekaran Raja
Keyword(s):  
Deep Learning ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Production Management ◽  
Detection System ◽  
Denial Of Service ◽  
Attack Detection ◽  
Sensitive Information ◽  
Smart Meters ◽  
Network Intrusion

Abstract The Industrial Internet of Things (IIoT), also known as Industry 4.0, has brought a revolution in the production and manufacturing sectors as it assists in the automation of production management and reduces the manual effort needed in auditing and managing the pieces of machinery. IoT-enabled industries, in general, use sensors, smart meters, and actuators. Most of the time, the data held by these devices is surpassingly sensitive and private. This information might be modified,
1
stolen, or even the devices may be subjected to a Denial of Service (DoS) attack. As a consequence, the product quality may deteriorate or sensitive information may be leaked. An Intrusion Detection System (IDS), implemented in the network layer of IIoT, can detect attacks, thereby protecting the data and devices. Despite substantial advancements in attack detection in IIoT, existing works fail to detect certain attacks obfuscated from detectors resulting in a low detection performance. To address the aforementioned issue, we propose a Deep Learning-based Two Level Network Intrusion Detection System (DLTL-NIDS) for IIoT environment, emphasizing challenging attacks. The attacks that attain low accuracy or low precision in level-1 detection are marked as challenging attacks. Experimental results show that the proposed model, when tested against TON IoT, figures out the challenging attacks well and achieves an accuracy of 99.97%, precision of 95.62%, recall of 99.5%, and F1-score of 99.65%. The proposed DL-TLNIDS, when compared with state-of-art models, achieves a decrease in false alarm rate to 2.34% (flagging normal traffic as an attack) in IIoT.

scholarly journals Robust Self-Adaptation Fall-Detection System Based on Camera Height

Sensors ◽  
2019 ◽  
Vol 19 (17) ◽  
pp. 3768 ◽  
Author(s):  
Kong ◽  
Chen ◽  
Wang ◽  
Chen ◽  
Meng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Detection System ◽  
Fall Detection ◽  
Daily Activities ◽  
Detection Methods ◽  
Depth Camera ◽  
Detection Accuracy ◽  
Data Set ◽  
Human Segmentation ◽  
Self Adaptation

Vision-based fall-detection methods have been previously studied but many have limitations in terms of practicality. Due to differences in rooms, users do not set the camera or sensors at the same height. However, few studies have taken this into consideration. Moreover, some fall-detection methods are lacking in terms of practicality because only standing, sitting and falling are taken into account. Hence, this study constructs a data set consisting of various daily activities and fall events and studies the effect of camera/sensor height on fall-detection accuracy. Each activity in the data set is carried out by eight participants in eight directions and taken with the depth camera at five different heights. Many related studies heavily depended on human segmentation by using Kinect SDK but this is not reliable enough. To address this issue, this study proposes Enhanced Tracking and Denoising Alex-Net (ETDA-Net) to improve tracking and denoising performance and classify fall and non-fall events. Experimental results indicate that fall-detection accuracy is affected by camera height, against which ETDA-Net is robust, outperforming traditional deep learning based fall-detection methods.

scholarly journals Network Attacks Detection Methods Based on Deep Learning Techniques: A Survey

2020 ◽  
Vol 2020 ◽  
pp. 1-17
Author(s):  
Yirui Wu ◽  
Dabao Wei ◽  
Jun Feng
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Attack Detection ◽  
Detection Methods ◽  
Generative Adversarial Network ◽  
Network Attacks ◽  
Adversarial Network ◽  
Fifth Generation ◽  
Learning Techniques ◽  
Benchmark Datasets

With the development of the fifth-generation networks and artificial intelligence technologies, new threats and challenges have emerged to wireless communication system, especially in cybersecurity. In this paper, we offer a review on attack detection methods involving strength of deep learning techniques. Specifically, we firstly summarize fundamental problems of network security and attack detection and introduce several successful related applications using deep learning structure. On the basis of categorization on deep learning methods, we pay special attention to attack detection methods built on different kinds of architectures, such as autoencoders, generative adversarial network, recurrent neural network, and convolutional neural network. Afterwards, we present some benchmark datasets with descriptions and compare the performance of representing approaches to show the current working state of attack detection methods with deep learning structures. Finally, we summarize this paper and discuss some ways to improve the performance of attack detection under thoughts of utilizing deep learning structures.

scholarly journals A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis

Electronics ◽  
2021 ◽  
Vol 10 (17) ◽  
pp. 2132
Author(s):  
Kyriakos D. Apostolidis ◽  
George A. Papakostas
Keyword(s):  
Neural Networks ◽  
Image Analysis ◽  
Deep Learning ◽  
Language Processing ◽  
Medical Image ◽  
Medical Image Analysis ◽  
Attack Detection ◽  
Detection Methods ◽  
Proper Function ◽  
Magnetic Resonance Imaging Mri

In the past years, deep neural networks (DNN) have become popular in many disciplines such as computer vision (CV), natural language processing (NLP), etc. The evolution of hardware has helped researchers to develop many powerful Deep Learning (DL) models to face numerous challenging problems. One of the most important challenges in the CV area is Medical Image Analysis in which DL models process medical images—such as magnetic resonance imaging (MRI), X-ray, computed tomography (CT), etc.—using convolutional neural networks (CNN) for diagnosis or detection of several diseases. The proper function of these models can significantly upgrade the health systems. However, recent studies have shown that CNN models are vulnerable under adversarial attacks with imperceptible perturbations. In this paper, we summarize existing methods for adversarial attacks, detections and defenses on medical imaging. Finally, we show that many attacks, which are undetectable by the human eye, can degrade the performance of the models, significantly. Nevertheless, some effective defense and attack detection methods keep the models safe to an extent. We end with a discussion on the current state-of-the-art and future challenges.

Sign in / Sign up

Export Citation Format

Share Document