Steganography Adaptation Model for Data Security Enhancement in Ad-Hoc Cloud Based V-BOINC Through Deep Learning

Abstract

AbstractCloud computing’s automation, scalability, and availability were vital features in the early days of digital transformation. Meanwhile, substantial concerns were expressed about cloud security and privacy. Due to the COVID-19 outbreak, several businesses have had serious issues speeding up their cloud migration efforts. This work intends to improve steganography in ad-hoc cloud systems using deep learning. This study is implemented in two phases.Phase 1: The ‘Ad-hoc Cloud System’ concept and deployment method were created using V-BOINC, a tool that allows developers to bypass application-level security checks, the implemented ad-hoc cloud system was compared Amazon AC2 and showed high evaluation rate in some matrices.Phase 2: We evaluate the data transmission security in ad-hoc cloud systems using a modified steganography with deep learning usage to replace or enhance an image-hiding system. In this study, the proposed model inputs data/images into the ad-hoc cloud system to guarantee high rate of data/image concealing. Statistically, a systematic steganography model hides lower message detection rates, the proposed deep steganography approach outperformed several attacks in the ad-hoc cloud environment.KeywordsCloud computingSteganographyEncryptionCloud cecurityDeep learning