<scp>EdDSA</scp> Based Network Data Authentication and Intrusion Detection System Using <scp>QDQN</scp>‐<scp>DPER</scp> With Hippopotamus Optimization

ABSTRACT Network security is essential for safeguarding sensitive information, and authentication plays a critical role in ensuring that only authorized users or processes gain access to protected resources. Traditional intrusion detection systems (IDS) rely heavily on signature‐based methods, which can only detect known threats, limiting their effectiveness in dynamic network environments. This paper proposes an advanced authentication and intrusion detection framework based on the Edwards‐curve digital signature algorithm (EdDSA) and quantum deep Q‐learning with distributed prioritized experience replay (QDQN‐DPER). The proposed system begins by validating user data through EdDSA authentication. Preprocessing steps, including the alternative ranking order method step two normalization (AROMAN) and handling missing values through a missing‐at‐random approach, are employed to prepare the data. Linear discriminant analysis (LDA), optimized by dipper‐throated optimization (DTO), is then used for dimensionality reduction. For attack detection, the QDQN‐DPER method, enhanced by the hippopotamus optimization algorithm (HOA), is utilized. The system performance is evaluated using standard metrics, including accuracy, precision, and F 1‐score, achieving values of 95.36%, 92.4%, and 95.51%, respectively. These findings demonstrate that the proposed model significantly improves security for wireless networks, offering an effective solution for detecting and preventing advanced cyber threats.