Customer attrition is a major issue that affects the telecom industry as it reduces the company’s revenues and the overall customer base. Solving this problem involves the use of accurate prediction models that utilize CRM data and machine learning algorithms. Though several research papers have been written and published on CCP in the telecom industry, the existing models lack reliability and accuracy. The use of sophisticated data mining and machine learning techniques has been widely practised for improving predictive models. Churn prediction models that exist have their problems in terms of accuracy and errors. It is still important to develop more sophisticated models that can work well with large data and give accurate predictions. Therefore, this work aims to offer the OKMSVM model for  multiclass cancer-type classification. The method applied for the dimensionality reduction pre-process is Kernel Principal Component Analysis (KPCA) and the feature selection pre-process is done using Ant Lion Optimization (ALO). This combination assists in improving the chance of the prediction and also the reduction of probable errors. The performance of the proposed OKMSVM model was compared with some of the most common churn prediction models such as HTLSVM, DNN, ICPCSF and other ML models. It was seen that the OKMSVM model outperformed other models with an accuracy of 91. 5%, an AUC of 85. Accurate, with a correlation coefficient of 0. 838. It further shows that this model is better than the current models in the market in estimating customer churn.

In this current scenario web application are widely using for various purpose like online shopping, online money transfer, e-bill payment, online mobile recharges etc. As per increasing the dependency on these web applications also raises the attacks on these applications. SQL injection Attacks (SQLIA) and Cross Site Scripting (XSS) are being a major problem for web applications. SQL injection Attack (SQLIA) is the most common type of vulnerability in which a malicious mind person is inserts its own crafted query as input for retrieving personal information about others sensitive users. In this paper, for detection and prevention of SQL injection attacks various techniques are described and perform a comparison between them.

In the phishing attack, the user sends their confidential information on mimic websites and face the financial problem, so the user should be informed immediately about the visiting website. According to the Third Quarter Phishing Activity Trends Report, there are 55,282 new phishing websites have been detected in the month of July 2014. To solve the phishing problem, a browser based add-on system may be one of the best solution to aware the user about the website type. In this paper, a novel browser based add-on system is proposed and compared its performance with the existing anti-phishing tools. The proposed anti-phishing tool 'ePhish' is compared with the existing browser based anti-phishing toolbars. All the anti-phishing tools have been installed in computer systems at an autonomous college to check their performance. The obtained result shows that if the task is divided into a group of systems, it can give better results. For different phishing features, the add-on system tool show around 97 percentage successful results at different case conditions. The current study would be very helpful to countermeasure the phishing attach and the proposed system is able to protect the user by phishing attacks. Since the system tool is capable of handling and managing the phishing website details, so it would be helpful to identify the category of the websites.

The term Phishing is a kind of spoofing website which is used for stealing sensitive and important information of the web user such as online banking passwords, credit card information and user’s password etc. In the phishing attack, the attacker generates the warning message to the user about the security issues, ask for confidential information through phishing emails, ask to update the user’s account information etc. Several experimental design considerations have been proposed earlier to countermeasure the phishing attack. The earlier systems are not giving more than 90 percentage successful results. In some cases, the system tool gives only 50-60 percentage successful result. In this paper, a novel algorithm is developed to check the performance of the anti-phishing system and compared the received data set with the data set of existing anti-phishing tools. The performance evaluation of novel anti-phishing system is studied with four different classification data mining algorithms which are Class Imbalance Problem (CIP), Rule based Classifier (Sequential Covering Algorithm (SCA)), Nearest Neighbour Classification (NNC), Bayesian Classifier (BC) on the data set of phishing and legitimate websites. The proposed system shows less error rate and better performance as compared to other existing system tools.

A novel multirate media access control based co-operative scheme has been proposed. It has been observed that any co-operative scheme gives a better performance only if the helper nodes selected to, relay the transmission from source to destination are reliable enough. Murad Khalid et.al has already proposed a protocol [24] where more than one helper nodes are selected to improve the reliability, so that if one fails the other can be used as a backup. But in this paper focus is on selection of reliable helpers. If a helper node has a high data rate, has successfully relayed traffic in the past and also has some minimum amount of energy left , not only for relaying traffic for others but also to conduct its own transmissions, then it acts as a suitable candidate to be chosen as a helper node. Such a co-operatives scheme enhances the throughput, reliability and overall performance of the network.Simulation has been conducted to show that the proposed scheme performs better than the

Wireless sensor networks (WSNs) are novel large-scale wireless networks that consist of distributed, self organizing, low-power, low-cost, tiny sensor devices to cooperatively collect information through infrastructure less wireless networks. These networks are envisioned to play a crucial role in variety of applications like critical military surveillance applications, forest fire monitoring, commercial applications such as building security monitoring, traffic surveillance, habitat monitoring and smart homes and many more scenarios. Node capture attack is one of the most dreadful security attack exist in wireless sensor networks. An adversary steals cryptographic key or other confidential information like node’s id etc from a captured node to compromise entire network. So, Security of wireless sensor network is an important issue for maintaining confidentiality and integrity of wireless links. Now-a-days, researchers are paying attention towards developing security schemes against Node capture attack. Our survey provides deep insights of existing techniques that enhance the attacking efficiency of the node capture attack in wireless sensor network. It also analyzes various detection and key pre-distribution schemes for inventing a new scheme to improve resilience against node capture attack.

In an advanced wireless network, trust is desirable for all routing protocols to secure data transmission. An enormous volume of important information communicates over the wireless network using trusted dynamic routing protocol, which is the enhancement of the DSR (Dynamic Source Routing) protocol to improve trust. Previously fuzzy logic, genetic algorithm, neural network has been used to modify DSR and good result has been obtained in few performance indicators and parameters. In this work an SVM based trusted DSR have been developed and better results have been presented. This new novel on demand trust based routing protocol for MANET is termed as Support vector machine based Trusted Dynamic Source Routing protocol, performance of STDSR has been improved in term of the detection ratio (%) at different mobility and no. of malicious node variation.

Chaotic system based message encryption system for wired and wireless networks broadly used in computer engineering, communication and network security, such as robotic systems, encryption, synchronization and genetic network. The main motive for developing the chaos based cryptosystem is to attain encryption with several compensation over the conventional encryption algorithms such as high security, speed, complexity, cost and quality assurance. These challenges encourage the researchers to develop novel chaos based data encryption techniques with digital logics dealing with encryption of messages for fast and secure communication networks. This effort provides a modified version of traditional data encryption algorithms to provide good quality and performance in a secure communication network environment. A cryptology technique is widely used in network security during communication. An avalanche effect is the attractive property of cryptography in which two different keys produce different cipher text for the same data information and also some Important properties related to chaotic systems are sensitivity to initial condition and nonlinearity, which makes two similar or slightly different keys to generate completely different cipher text to produce confusion. It has been proposed a novel fast & secure encryption Technique which uses the chaotic map function to generate the different multiple keys and shows that negligible difference in parameters of chaotic function generate completely different keys as well as cipher text. Cryptanalysis of the proposed algorithm shows the strength and security of algorithm and keys.