Port scanning is a phase in footprinting and scanning; this comes in reconnaissance which is considered as the first stage of a computer attack. Port scanning aims at finding open ports in a system. These open ports are exploited by attackers to carry out attacks and exploits. There are a number of tools to scan for open ports. However, very few tools are present to detect port scanning attempts.The goal of this project is to identify port scan attempts and find out information about the machine from where port scan attempts were made. If an attack takes place after the port scan, the collected information would help in bringing the criminal to justice. We hope that this work will add an additional layer of defense by identifying port scan attempts thereby indicating that an attack may follow.

No abstract

Deep learning models are widely used for solving problems in different applications. Especially Convolutional Neural Network (CNN) based models are found suitable for medical image analysis. As brain stroke is increasing in alarming rate, it is essential to have better approaches to detect it in time. Brain MRI is one of the medical imaging technologies widely used for brain imaging.we proposed certain advancements to well-known deep learning models like VGG16, ResNet50 and DenseNet121 for enhancing brain stroke detection performance. These models are optimized based on the brain stroke detection problem in hand as they are not specialized for a specific problem. We proposed an algorithm, named Deep Efficient Stroke Detection (ESD), that exploids enhanced deep learning models in pipeline. The experimental results revealed that there is performance improvement with optimized models. Highest accuracy is achieved by ResNet50 with 95.67%.

Abstract:Cloud computing service is one of the most emerging research area in the field of cloud environment. It also emerged as a new platform for managing, deploying and provisioning large scale data. However, the access of user in cloud node or data storage point is restricted to a certain condition. Whereas, several encryption methodologies are utilized in the cloud for improving the security and also to reduce the computation time, but most of the methodologies requires high processing unit. To overcome this concern, an effective cloud storage system is developed in this research paper. Here, an Enhanced-Elliptic Curve Diffie Hellman (E-ECDH) approach is utilized for encrypting and decrypting the data with low computational time. The E-ECDH method generates the key without any complex program that helps in limited use of resources. The encryption and decryption time of the E-ECDH is decreased by using the less complex value. Finally, the experimental outcome showed that the proposed approach improved the security of the cloud system up to 0.11-0.03% of success rate compared to the other existing methodologies.