Iris recognition systems have emerged as a pivotal biometric technology, offering high reliability for secure Authentication System. In this study, we emphasize the indispensable role of iris recognition within authentication frameworks, particularly in response to global health emer-gencies such as the COVID-19 pandemic, which underscored the need for contactless and health-conscious authentication solutions. We propose an advanced secure iris recognition framework that leverages a convolutional neural network (CNN) based on the EfficientNetB7 architecture for robust feature extraction. To ensure enhanced security, the extracted features are encrypted using Fully Homomorphic Encryption (FHE) and organized within a Bloom Filter (BF), thereby satisfying stringent security and privacy requirements. The effectiveness of the proposed system is validated on two benchmark datasets: CASIA-Iris-Syn and IITD_V1. Our approach achieves outstanding results, attaining an accuracy of 0.9998 with an Equal Error Rate (EER) of 0.001 on CASIA-Iris-Syn, and an accuracy of 0.9898 with an EER of 0.024 on IITD_V1. Comparative analysis against existing verification systems demonstrates that the proposed framework not only achieves superior accuracy and security but also addresses the increasing demand for resilient and privacy-preserving biometric authentication systems.

In current state-of-the-art intrusion detection systems (IDSs), models are trained to detect the repetitive behavior of data traffic. This leads to the problem of ignoring rare yet important attacks. To solve the problem stated above, a risk-gated security attention (RGSA) architecture is proposed. The initialization of the risk estimator based on the CVE/CVSS severity score enables the attention network to detect important yet rare patterns. Furthermore, a tier-aware focal loss is proposed to mitigate security threats in the real world without any data augmentation process. Evaluations were conducted on held-out 80/20 test splits of the CIC-IDS2017, CIC-IDS2018, and CIC-IoT2023 datasets. The calibrated binary detection process reached false negative rates (FNRs) of 0.50% and 0.40% on the CIC-IDS2017 and CIC-IDS2018 datasets, respectively, remaining below the 1.0% FNR operational target adopted in this study. For micro-support critical threats, precise discrete analysis had to be applied to maintain statistical validity. Also, weighted F1-scores of at least 99.65% were consistently achieved for all testbeds analyzed. This network contains 284,317 trainable parameters and strictly avoids the creation of any synthetic samples through complete rejection of synthetic oversampling. The findings indicate that adding priors for security tiers to the attention process is favorable for moving towards an impact-based threat management approach.