AES-Based Encoding and Decoding Images using MATLAB
A Novel Technique of Sign Language Recognition System using Machine Learning for Differently Abled Person
Implementation of Machine Learning Techniques for Depression in Text Messages: A Survey
A Study of Ransomware Attacks on Windows Platform
Techniques of Migration in Live Virtual Machine and its Challenges
Efficient Agent Based Priority Scheduling and LoadBalancing Using Fuzzy Logic in Grid Computing
A Survey of Various Task Scheduling Algorithms In Cloud Computing
A Viable Solution to Prevent SQL Injection Attack Using SQL Injection
A Computational Intelligence Technique for Effective Medical Diagnosis Using Decision Tree Algorithm
Integrated Atlas Based Localisation Features in Lungs Images
Security of the vehicles are challenging factor. Nowadays, users prefer comfort and a safe environment for their vehicles. With the development in technology, ancient standard keys for vehicles have been modified by Remote Keyless Entry System (RKES). This new scenario boosts user's safety and convenience. During the development of this new environment, attackers have also found new ways to hack the RKES. In this paper, a novel technique for secure authentication using blockchain technology has been developed which will provide a more secure way for keyless access. Our model is based on a time comparison of various hash algorithms which are widely used in encrypted and blockchain processes for authentication. Many tests were conducted to check the time complexity of hash algorithms for providing a clear outlook about the security and time complexity.
Network Intrusion Detection (NID) has become a prominent topic nowadays with the increased use of technology and networks. In this study, a novel hybrid approach for network intrusion detection has been presented using Extreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) networks. The benchmark NSL-KDD dataset has been used. A number of minimal feature sets were created using XGBoost for feature selection and the effects of using them in an LSTM model for detecting whether or not the network features belong to an attack were studied. It has been observed that XGBoost feature selection could be used to create minimal feature sets with very high feature reduction ratios to use in an LSTM model for NID in order to have a clear understanding of the features the model uses to learn, to achieve shorter training times and a good accuracy value close to that achieved using all the features in the dataset utilizing lower space. The findings of this study can be used for building better NID systems using deep neural networks for real-time NID. Also, they can be utilized to develop a first layer of defense for alerting the users about possible threats in real-time.
Software cryptography is a great utility for many applications. If properly implemented, it provides a good level of security. However, some applications may require a greater level of secrecy and privacy, in such cases hardware cryptography would be more adequate. This paper illustrates the integration of hardware cryptosystem and instant messaging desktop application. Today, people use online chat platforms for sharing their private and business information. Such information can be attacked by hackers. The present instant messenger systems lack authenticity, confidentiality and integrity, and such disadvantages can be collaboratively eliminated through this proposed idea. Results will be tested to check whether the proposed model is resistant to adversarial attacks and also by considering cryptographic test like Hamming distance and NIST SP800-22.
The constant growth of phishing and the rise in the number of phishing websites that could not be detected by search engines have led to the fact that individuals and organizations around the world are increasingly exposed to various cyber attacks. Phishing attacks are one of the most common and least protected security threats these days in the form of sealed browsers. We have techniques that are used to analyze textual URLs and identify indirect claims that indicate phishing attacks. Consequently, more effective phishing detection is required for improved cyber defense. Phishing attackers always use new and sophisticated techniques to deceive online customers. Hence, it is necessary that the anti-phishing solution should be an intelligent real-time system and fast. Threat intelligence and behavioral analytics systems support organizations to prevent phishing attacks. Our approach is novel compared to previous works; we collect phishing websites through various browsers using mini-bots or crawlers. The result will be used as the main source for linguistic analysis of the contents used for malicious attacks. A model will be built that involved in phishing detection and those websites will be avoided in real-time environments.
To perform sentiment analysis, a number of machine learning and deep learning approaches were utilised in this paper to address the challenge of sentiment categorization on the Twitter dataset. Finally, on the Kaggle's public leaderboard, a majority vote ensemble approach has been used using 5 of our best models to get a classification accuracy of 83.58 percent. Various strategies for analysing sentiment in tweets (a binary classification problem) have been compared. The training dataset should be a CSV file with the following columns: tweet_id, sentiment, tweet, where tweet_id is a unique integer identifying the tweet, sentiment is either 1 (positive) or 0 (negative), and tweet is the tweet enclosed within "". For library requirements particular to some methods, such as Keras with TensorFlow backend for Logistic Regression, MLP, RNN (LSTM), and CNN for XGBoost, we used the Anaconda Python distribution. Preprocessing, baselines, Naive Bayes, Maximum Entropy, Decision Trees, Random Forests, Multi-Layer Perception, and other techniques that are implemented.