A hybrid security model for data protection in public cloud computing.

Abstract

This thesis sought to address the following objectives: assess security threats and attacks on data in public cloud computing, assess existing techniques for securing data in public cloud environments, develop a hybrid algorithm to enhance data security in public cloud computing, and evaluated the effectiveness of the proposed hybrid algorithm. This study adopted a positivist research paradigm and employed both descriptive and data science methodologies. Secondary data was collected from peer-reviewed journal articles, conference proceedings, and books, while high-quality images were sourced from the University of Southern California Signal and Image Processing Institute database for algorithm test simulations. Encryption was applied to numerical data before embedding it into cover images, and data analysis was conducted using content analysis, gap analysis, visual quality assessment, statistical evaluation, and comparisons with baseline algorithms. Simulations were performed using MATLAB R2021a on six color images. The study identified various threats to data in public cloud computing, including insecure APIs, legal and compliance issues, data corruption, code injection, insider threats, mobile malware, phishing and social engineering, denial of service, man-in-the-middle attacks, SQL injection, and cross-site scripting. These threats can be mitigated through robust security frameworks such as input validation, encryption, access controls, and continuous monitoring, along with organizational strategies like employee training, legal compliance audits, and regular vulnerability assessments. Techniques for securing data in public cloud environments include cryptographic algorithms like Blowfish, Twofish, RSA, digital signatures, homomorphic encryption, authentication, and data hiding methods. The proposed hybrid algorithm integrated Least Significant Bit substitution with Paillier Homomorphic Encryption and was evaluated using Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), entropy, and histogram analysis. Results showed low MSE values (0.000023–0.00012), high PSNR values (87.3–94.57), and entropy values ranging from 6.4207 to 7.5937, indicating minimal distortion, high reconstruction quality, and strong data complexity. The algorithm maintained high visual and statistical fidelity post-embedding, with perfect correlation and stable entropy values, while minor chi-square fluctuations suggested localized changes without compromising imperceptibility or robustness. Overall, the hybrid algorithm proved effective for secure data hiding in public cloud computing by preserving image quality and ensuring statistical integrity.