Detection and mitigation of DDoS attacks in SDN: A comprehensive review, research challenges and future directions

Software-defined network (SDN) is a network architecture that used to build, design the hardware components virtually. We can dynamically change the settings of network connections. In the traditional network, it's not possible to change dynamically, because it's a fixed connection. SDN is a good approach but still is vulnerable to DDoS attacks. The DDoS attack is menacing to the internet. To prevent the DDoS attack, the machine learning algorithm can be used. The DDoS attack is the multiple collaborated systems that are used to target the particular server at the same time. In SDN control layer is in the center that link with the application and infrastructure layer, where the devices in the infrastructure layer controlled by the software. In this paper, we propose a machine learning technique namely Decision Tree and Support Vector Machine (SVM) to detect malicious traffic. Our test outcome shows that the Decision Tree and Support Vector Machine (SVM) algorithm provides better accuracy and detection rate.

Detection of Distributed Denial of Service Attacks in SDN using Machine learning techniques

Diabetes is one of the most common and hazardous diseases, which can affect almost every organ in the body. Diagnosis of diabetes requires determining all vital parameters related to the disease. However, the nature of the data from those parameters is very uncertain, affecting the process of disease diagnosis. This article proposes an intelligent fuzzy inference rule‐based predictive diabetes diagnosis model (IFIR_PDDM), providing content recommendations to patients with diabetes. The suggested model employs an inference technique that medical specialists have validated for recommendations. IFIR_PDDM comprises three elements used to forecast the risk of diabetes disease. Initially, a fuzzy membership function utilizes medical recommendations and statistical methodologies. Medical specialists then validate the mining‐based rules using a decision tree rule induction technique. The proposed model predicts the risk of diabetes disease using fuzzy inference based on Mamdani's technique. Based on this information, the recommendations for a normal life, nutrition, exercise, and medications are given to patients. We used an electronic health record (EHR) medical and clinical dataset from the PIMA Indian Diabetes dataset to develop our proposed model and assess its performance. The proposed model takes less time for diabetes diagnosis, and the expert recommendation system uses the fuzzy inference method.

An intelligent fuzzy inference rule‐based expert recommendation system for predictive diabetes diagnosis

A distributed denial of service (DDoS) attack represents a major threat to service providers. More specifically, a DDoS attack aims to disrupt and deny services to legitimate users by overwhelming the target with a massive number of malicious requests. A cyberattack of this kind is likely to result in tremendous economic losses for businesses and service providers due to increasing both operating and financial costs. In recent years, machine learning (ML) techniques have been widely used to prevent DDoS attacks. Indeed, many defense systems have been transformed into smart and intelligent systems through the use of ML techniques, which allow them to defeat DDoS attacks. This paper analyzes recent studies concerning DDoS detection methods that have adapted single and hybrid ML approaches in modern networking environments. Additionally, the paper discusses different DDoS defense systems based on ML techniques that make use of a virtualized environment, including cloud computing, software-defined network, and network functions virtualization environments. As the development of the Internet of Things (IoT) has been the subject of significant research attention in recent years, the paper also discusses ML approaches as security solutions against DDoS attacks in IoT environments. Furthermore, the paper recommends a number of directions for future research. This paper is intended to assist the research community with the design and development of effective defense systems capable of overcoming different types of DDoS attacks.

/pdf/machine-learning-approaches-for-combating-distributed-denial-4br43qv4ja.pdf

Machine Learning Approaches for Combating Distributed Denial of Service Attacks in Modern Networking Environments

Nowadays, Health care is considered as an important aspect of our everyday lives. To address the emerging health-related challenges, this research wprk has utilised the advanced digital technologies to develop a health tracking analyzer. Recently, the use of mobile phones and other gadgets has increased unprecedentedly by creating a significant impact on the mobile health care. Mobile Health applications serve a large number of consumers. The main aim of this research work is to create a health tracking analyzer so that any patient or anybody who is concerned about their health may be readily tracked by their doctors or health care providers. This loT -based device aids in critical situations by avoiding illness transmission and providing health diagnoses even when the doctor is at a considerable distance away from the patient. Many people are receiving therapy for a variety of issues, including heart disease. The proposed model plays a vital role in checking and storing the healthcare-related data in server by using a Wi-Fi Module. Furthermore, the proposed device tracks the heartbeat and temperature by using the detectors and also a microcontroller is attached to the sensor. To frequently update the condition of patient's, the microcontroller is linked with LCD display and Wi-Fi to transfer the information to the database. By employing an inter connection, the pulse rate and temperature can also be analyzed. The gadget will exchange the readings from the sensor to the cloud and the information gathered will also remain accessible. The proposed database analyzes the received information and alerts the patient through buzzer.

Indigenous Health Tracking Analyzer Using IoT

Software Defined Network (SDN) provides a promising solution over traditional networks by decoupling the control plane and network plane. With the help of this feature, controller can get global view of the entire network. Since the controller acts as a core part of the SDN environment, there is a serious threat towards the controller in terms of security. A Distributed Denial of Service (DDoS) attack is the most potential attack in SDN environment. DDoS attack prevents the authorized user to access the available resources for infinite amount of time. In this paper, we have proposed the hybrid machine learning model to protect the controller from DDoS attacks. And our experimental results clearly manifest that the hybrid machine learning model provides more accuracy, detection rate and less false alarm rate compared to simple machine learning models.

Detection of DDoS Attack on SDN Control plane using Hybrid Machine Learning Techniques

The objective of data compression is to extract the main features of the data and to restore the decompressed data from latent space ie, compressed data without any quality or noise In this paper, a Convolutional LSTM model is proposed to reduce the redundancy data and unnecessary information in the data set The proposed methodology normalizes the picture to reduce blur and noises, with a compression ratio of 50% The Convolutional LSTM model is compared with other models such as autoencoder, denoising autoencoder, convolutional neural network and our present work shows better RMSE compared to the other models Datasets like MNIST and other datasets are used for testing and training the images

Competent Ultra Data Compression By Enhanced Features Excerption Using Deep Learning Techniques

Providing security measures to any real time application is the one of the difficult and important task Biometric is one of the increasingly used technologies to identify and verify the user It positively provides better security against the identity theft Biometric technique helps to identify each individual by analysing his/her unique behavioural and physiological features But in some practical situations, biometric techniques fail to meet the security requirements Spoofing attacks is one of the major threats in real time environment Attackers are using the forged biometric traits to gain the access of victim’s account and data In this paper, we have analysed need for biometric techniques compared to traditional techniques for authentication purpose We have also reviewed about general biometric techniques such as fingerprint, iris-scan, retina-scan, facial recognition, palm scan, voice recognition, signature-based, gait biometrics by analysing both advantages and drawbacks This paper also discussed about security threats and its positive countermeasures in general biometric techniques

Analysis of Security Threats and Countermeasures for various Biometric Techniques

The Discrete Wavelet transform is one of the best tools for signal and data analysis, It requires efficient hardware implementation in the real-time applications. The submissions established in the field of imaging necessitates compacted architecture. In DWT discrete sampling is accomplished for the wavelets. In this paper, the VLSI implementation of HAAR wavelet-based image compression is proposed and designed. HAAR wavelet transform is one of the easiest methods for image compression because it has coefficients as either 1 or −1. In this work software alone is used for the compression together with optimizing it with a continuous optimization algorithm and provides a hardware-free architecture with low cost. The VHDL work is carried out in Xilinx Platform and provides a truncated power architecture for a concrete application. The same VHDL architecture can also be instigated in FPGA which will harvest hardware effectual compromising outcomes.

VLSI Implementation of Image Compression using TSA Optimized Discrete Wavelet Transform Techniques

Background:One of the primary concerns in online social networks is fake image or fake colorized image diffusion, which allows anyone to add, remove, and alter the images.Purpose:Till now it is not possible to develop a model or a technique that can accurately recognize or categorize images as fake or genuine.Method:In this paper we are trying to utilize the flood fill algorithm to In this paper we are trying to utilize the flood fill algorithm to highlight the forged object in the image and a Deep Learning based solution is proposed to detect whether the image is fake or genuine. We collect twitter dataset, which is given as input to the deep learning models and train them to identify whether the image is fake or genuine.Result:Experimental evaluations showed that the proposed framework can detect the fake images that have been diffused in Twitter with 96% accuracy.

K. Muthamil Sudar

Papers

Detection of DDoS Attack on SDN Control plane using Hybrid Machine Learning Techniques

Competent Ultra Data Compression By Enhanced Features Excerption Using Deep Learning Techniques

Analysis of Security Threats and Countermeasures for various Biometric Techniques

VLSI Implementation of Image Compression using TSA Optimized Discrete Wavelet Transform Techniques

Fake Image Detection in Twitter using Flood Fill Algorithm and Deep Neural Networks