Symbiotic Organisms Search Optimization based Faster RCNN for Secure Data Storage in Cloud

Abstract

Because of the Internet of Things (IoT) and wearable devices, information obtained is subject to cyber attacks, making intrusion detection an essential component. The increased number of attacks on IoT devices exposes them to ongoing exploitation and data theft. Mirai, denial of Service (DoS), scan, etc are the major types of attacks conducted on IoT. Traditional attack detection algorithms have more disadvantages like lack of adaptability in all scenarios, low local minima computational complexity, etc. Thus developing a method that is suitable for all environments and has good convergence speed is taken as the motivation of this study. This paper presents a novel Symbiotic Organisms Search Algorithm (SOSA) optimized Faster region-based convolutional neural network (FRCNN) for attack detection and data type classification. The data to be stored in the cloud is analyzed whether they have restricted access, confidential, or unclassified. Depending upon the variety of data, the Optimal homomorphic encryption (OHE) approach is provided for security. The key selection process is done by an Elastic Collision Seeker Optimization Algorithm (ECSOA) which offers secure access to the data owner and prevents the data from unauthorized access. The model is optimized using the algorithm which improves the feature extraction performance. The effectiveness of the proposed model in attack detection is evaluated using two datasets namely the CSE-CIC-ID2018 dataset and the IoTID20 dataset. When compared to the existing techniques, the proposed model offers optimal performance in terms of multiclass attack detection.