Journal of Basic and Applied Research International

The rapid growth of telemedicine has increased the demand for secure and efficient transmission of sensitive medical data, where image encryption plays a pivotal role in protecting patient privacy. Cryptographic substitution boxes (S-boxes) are fundamental components in symmetric encryption systems, directly influencing their resistance to cryptanalytic attacks. Recent research has focused on leveraging metaheuristic algorithms and chaotic systems to enhance S-box cryptographic strength, enabling secure and real-time medical image transmission. In this paper, a multi-objective Nonlinear Self-Adaptive Particle Swarm Optimization (NSPSO) framework integrated with a Hybrid Logistic–Sine chaotic map is proposed for the evolution of cryptographically robust S-boxes. The proposed approach is rigorously evaluated using established cryptographic metrics, including nonlinearity, differential uniformity, and autocorrelation, to ensure resistance against linear and differential cryptanalysis. The optimized S-boxes are then employed in a secure medical image encryption scheme, whose performance is validated through comprehensive statistical, entropy-based, and robustness analyses. The experimental results confirm the scheme’s strong security characteristics, high key sensitivity, and reliable lossless decryption. Owing to these capabilities, the proposed framework offers a practical and scalable solution for safeguarding patient data in real-time telemedicine environments, thereby enhancing trust and security in digital healthcare services.